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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penetrating
    -0.07
    Initially
    -0.07
    (column
    -0.06
    udson
    -0.06
     faded
    -0.06
    _CURSOR
    -0.06
     enjo
    -0.06
    posit
    -0.06
     chapter
    -0.06
    xae
    -0.06
    POSITIVE LOGITS
     بدن
    0.06
    chematic
    0.06
     телеф
    0.06
    684
    0.06
     productList
    0.06
    ние
    0.06
    074
    0.06
    Sil
    0.06
    eczy
    0.06
    tableFuture
    0.06
    Act Density 0.010%

    No Known Activations