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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief, opinion, or acknowledgment in discussions

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

    thoughts or beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     formales
    -0.33
     chance
    -0.33
    ⅘
    -0.33
    Попис
    -0.33
    [^
    -0.32
    kolen
    -0.32
    XMLSchema
    -0.31
    uens
    -0.31
     serons
    -0.31
     morado
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    0.56
    CppMethod
    0.53
    bewerken
    0.52
    =$?
    0.50
    "");
    0.49
    "):
    0.49
     kasarigan
    0.49
    сылкі
    0.48
    '):
    0.48
     AttributeSet
    0.48
    Act Density 0.530%

    No Known Activations