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

    Neuronpedia

    INDEX
    Explanations

    blocks of code and programming language structures

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

    foreign and technical words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.53
    備
    -0.41
    IGENCE
    -0.39
    HasAnnotation
    -0.39
    kommen
    -0.38
    -0.37
     previous
    -0.35
    iprot
    -0.35
    namt
    -0.34
    fla
    -0.34
    POSITIVE LOGITS
    engeti
    0.51
    0.49
     florales
    0.44
    gamepad
    0.43
    esistenza
    0.43
    tagHelperRunner
    0.42
     nonUne
    0.41
     mentales
    0.41
    tatuajes
    0.41
     فريبيس
    0.40
    Act Density 0.017%

    No Known Activations