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

    Neuronpedia

    INDEX
    Explanations

    say ending with ")"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sheikh
    -0.06
    相同
    -0.06
    なる
    -0.06
    userid
    -0.06
     meetings
    -0.06
     العمل
    -0.06
     sharks
    -0.06
    alker
    -0.06
    yper
    -0.06
     monitored
    -0.06
    POSITIVE LOGITS
    \Validation
    0.07
    _bias
    0.07
    InputChange
    0.07
    _MSB
    0.06
    _undo
    0.06
    \Api
    0.06
    _places
    0.06
    _sampling
    0.06
     PdfP
    0.06
     FUCK
    0.06
    Act Density 0.011%

    No Known Activations