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

    Neuronpedia

    INDEX
    Explanations

    View

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reverso
    -0.72
     définiti
    -0.70
     nakalista
    -0.66
    BaseAdapter
    -0.66
    AlterField
    -0.64
     vectorielles
    -0.64
    xad
    -0.63
    PhysRevD
    -0.63
     grecque
    -0.62
     Référence
    -0.61
    POSITIVE LOGITS
     sink
    0.73
     sinks
    0.60
     die
    0.60
    DoubleQuotes
    0.55
    sink
    0.54
     sank
    0.50
     bu
    0.49
     settle
    0.49
     lit
    0.46
    Die
    0.45
    Act Density 0.000%

    No Known Activations