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

    Neuronpedia

    INDEX
    Explanations

    indelible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ادامه
    -0.07
    ấp
    -0.07
    生命
    -0.07
    _WM
    -0.06
    ضای
    -0.06
     Cheese
    -0.06
    iliki
    -0.06
    ận
    -0.06
    lena
    -0.06
     preach
    -0.06
    POSITIVE LOGITS
     dick
    0.07
    .seek
    0.07
     fseek
    0.06
    (sin
    0.06
     десяти
    0.06
    increment
    0.06
     arithmetic
    0.06
     uid
    0.06
     Arithmetic
    0.06
     admon
    0.06
    Act Density 0.117%

    No Known Activations