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

    Neuronpedia

    INDEX
    Explanations

    Contrasting statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SharedPreferences
    -0.07
    .accept
    -0.07
    нув
    -0.06
    caf
    -0.06
    พล
    -0.06
     audiences
    -0.06
    ,{
    -0.06
     Federation
    -0.06
    <float
    -0.06
    .move
    -0.06
    POSITIVE LOGITS
     behalf
    0.07
     เป
    0.06
     نفسه
    0.06
     bigotry
    0.06
    .gridx
    0.06
     paperback
    0.06
     bahwa
    0.06
     getMenu
    0.06
    iques
    0.06
     آن
    0.06
    Act Density 0.019%

    No Known Activations