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

    Neuronpedia

    INDEX
    Explanations

    Actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hypotheses
    -0.07
     silenced
    -0.06
    accumulator
    -0.06
    لمات
    -0.06
    .gov
    -0.06
    $output
    -0.06
     Europa
    -0.06
     ав
    -0.06
     boxes
    -0.06
     Nak
    -0.06
    POSITIVE LOGITS
    ています
    0.07
    ्तम
    0.06
    ügen
    0.06
    _QUOTES
    0.06
     diss
    0.06
     isset
    0.06
    argout
    0.06
    .MULT
    0.06
    anych
    0.06
    woff
    0.06
    Act Density 0.153%

    No Known Activations