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

    Neuronpedia

    INDEX
    Explanations

    parentheses and the number 1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     threshold
    -0.10
    _THRESHOLD
    -0.09
    threshold
    -0.08
     Threshold
    -0.08
    Threshold
    -0.08
    _threshold
    -0.07
     marriage
    -0.07
    _TRIGGER
    -0.07
     commander
    -0.07
    ETA
    -0.07
    POSITIVE LOGITS
     necesitar
    0.09
    不知道
    0.09
     desconoc
    0.08
     UNKNOWN
    0.08
     perlu
    0.08
     unfore
    0.08
     sollic
    0.08
    .Unknown
    0.08
    itut
    0.08
     தெரிய
    0.07
    Act Density 0.003%

    No Known Activations