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

    Neuronpedia

    INDEX
    Explanations

    .SH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     typing
    -0.08
     Clothes
    -0.08
     Tops
    -0.07
    测
    -0.07
    
    -0.06
     Mercury
    -0.06
    女性
    -0.06
     Ful
    -0.06
    RX
    -0.06
    c
    -0.06
    POSITIVE LOGITS
    DBus
    0.07
    .POST
    0.07
     coveted
    0.06
    ",__
    0.06
    strftime
    0.06
     sortable
    0.06
    _Bool
    0.06
    .settings
    0.06
     veya
    0.06
    /student
    0.06
    Act Density 0.002%

    No Known Activations