Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of positive experiences and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation or "I"

    np_acts-logits-general · gemini-2.0-flash

    phrases describing understanding or confusion about something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.42
    AnimationsModule
    -0.41
    CppCodeGen
    -0.40
     крайне
    -0.38
    LEncoder
    -0.36
     scrittore
    -0.36
     asimismo
    -0.35
    pecha
    -0.35
    NewUrlParser
    -0.35
     dàng
    -0.35
    POSITIVE LOGITS
     ddelweddau
    0.50
     invokingState
    0.47
     Exacts
    0.47
    IVEREF
    0.46
    ngths
    0.44
    pagation
    0.44
     Infórmanos
    0.42
    polation
    0.41
    serum
    0.41
    school
    0.40
    Act Density 0.266%

    No Known Activations