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

    Neuronpedia

    INDEX
    Explanations

    how to do something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wh
    -0.07
    ordinator
    -0.07
    вид
    -0.06
    ited
    -0.06
     ['
    -0.06
    [level
    -0.06
    $a
    -0.06
    .;
    -0.06
    .flag
    -0.06
    ована
    -0.06
    POSITIVE LOGITS
     prezident
    0.07
     scripted
    0.07
    Kon
    0.07
     perfect
    0.06
    198
    0.06
     Reform
    0.06
    StyleSheet
    0.06
     preservation
    0.06
     Cabr
    0.06
     Kon
    0.06
    Act Density 0.114%

    No Known Activations