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

    Neuronpedia

    INDEX
    Explanations

    versions/modifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pe
    -0.08
     continents
    -0.08
     sogenannten
    -0.07
    eil
    -0.07
     Phil
    -0.07
     Var
    -0.07
    edoria
    -0.07
     Stockholm
    -0.07
    ianchi
    -0.07
     viktig
    -0.07
    POSITIVE LOGITS
     संस्करण
    0.11
     बनाउन
    0.11
     બનાવી
    0.10
    版本
    0.10
     fácilmente
    0.09
     બનાવવા
    0.09
    -friendly
    0.09
     बनाए
    0.09
     варианты
    0.09
     उपाय
    0.09
    Act Density 0.012%

    No Known Activations