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

    Neuronpedia

    INDEX
    Explanations

    deals with sensitive topics or policy violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大きさ
    0.46
     tragedies
    0.45
     cupr
    0.41
     guía
    0.41
     quaisquer
    0.40
    ᕝ
    0.40
    五十
    0.39
     drugih
    0.39
     uppermost
    0.39
     név
    0.39
    POSITIVE LOGITS
     Requires
    0.54
    requires
    0.52
     requires
    0.50
    Requires
    0.49
     this
    0.47
    this
    0.47
     necessitates
    0.46
     требует
    0.46
     अनियमित
    0.45
     sezon
    0.43
    Act Density 0.030%

    No Known Activations