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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mary
    -0.07
     Rams
    -0.06
    -self
    -0.06
    ams
    -0.06
    oter
    -0.06
    ít
    -0.06
     Madagascar
    -0.06
     tarım
    -0.06
    ichni
    -0.06
     aspiration
    -0.06
    POSITIVE LOGITS
    .binding
    0.07
    ле
    0.07
    Bl
    0.06
    gabe
    0.06
    _hint
    0.06
     Efficiency
    0.06
     eruption
    0.06
     đã
    0.06
    ponses
    0.06
    _auc
    0.06
    Act Density 0.002%

    No Known Activations