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

    Neuronpedia

    INDEX
    Explanations

    Scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SWITCH
    -0.08
    [df
    -0.08
     JK
    -0.07
    oses
    -0.06
    ButtonModule
    -0.06
     wl
    -0.06
     -(
    -0.06
     naveg
    -0.06
     partir
    -0.06
     hor
    -0.06
    POSITIVE LOGITS
    larda
    0.07
     acciones
    0.06
     accomplishment
    0.06
    heid
    0.06
     فإن
    0.06
    //================================================================
    0.06
     QU
    0.06
    形成
    0.06
    .resume
    0.06
     sizi
    0.06
    Act Density 0.139%

    No Known Activations