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

    Neuronpedia

    INDEX
    Explanations

    actions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꯋ
    0.79
    0.77
     stockno
    0.75
    йки
    0.74
     Atkinson
    0.74
    0.72
     Hodgson
    0.71
    GRect
    0.70
     ANSI
    0.70
    తున్న
    0.70
    POSITIVE LOGITS
    a
    0.85
    est
    0.78
    estado
    0.76
     anteriormente
    0.76
     ранее
    0.75
     dov
    0.75
     حاج
    0.75
    take
    0.75
    opens
    0.75
     momen
    0.73
    Act Density 0.000%

    No Known Activations