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

    Neuronpedia

    INDEX
    Explanations

    assignments and variables in code

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

    code from various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.65
    AndEndTag
    -0.60
    elemField
    -0.54
     ویکی‌پدی
    -0.54
     Joystick
    -0.52
    jenost
    -0.52
    ffions
    -0.52
    CastException
    -0.51
    DockStyle
    -0.51
    Kjelder
    -0.51
    POSITIVE LOGITS
    OCCURRED
    0.41
     therefore
    0.38
     accordingly
    0.37
    WebVitals
    0.36
     thereof
    0.35
     consequently
    0.34
    そこから
    0.32
     daar
    0.32
    それを
    0.32
    それに
    0.31
    Act Density 0.050%

    No Known Activations