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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abuse
    -0.07
    اوت
    -0.07
    745
    -0.07
    アルバ
    -0.06
    439
    -0.06
     sailors
    -0.06
    IOD
    -0.06
    -INFRINGEMENT
    -0.06
    Compact
    -0.06
    -null
    -0.06
    POSITIVE LOGITS
     {}↵
    0.07
    .concatenate
    0.06
    .MOUSE
    0.06
    objc
    0.06
    yasal
    0.06
     roman
    0.06
    ρωπα
    0.06
    个
    0.06
     ответ
    0.06
    /{{$
    0.06
    Act Density 0.010%

    No Known Activations