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

    Neuronpedia

    INDEX
    Explanations

    1950 and related years/events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    be
    -1.77
     adicional
    -1.76
    ᠂
    -1.72
    ೣ
    -1.72
    沇
    -1.71
     vehemently
    -1.70
     different
    -1.70
    溷
    -1.70
     become
    -1.69
     vettoriale
    -1.65
    POSITIVE LOGITS
    饸
    1.83
    謦
    1.78
    彇
    1.77
    鹋
    1.75
    ⡰
    1.75
    changers
    1.74
    퐿
    1.74
    祧
    1.70
    姽
    1.69
    颪
    1.69
    Act Density 0.016%

    No Known Activations