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

    Neuronpedia

    INDEX
    Explanations

    what's going on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.18
    ूव
    0.97
    ه
    0.94
    ો
    0.93
     occurrences
    0.87
    ल
    0.87
    ண்டு
    0.86
     nothing
    0.86
     happening
    0.82
    ம்
    0.82
    POSITIVE LOGITS
    苳
    0.81
     societ
    0.80
    Testables
    0.80
     Capsule
    0.79
    礡
    0.78
    ائلة
    0.78
    क्षित
    0.77
    გუ
    0.77
    Qui
    0.76
     Broch
    0.76
    Act Density 0.014%

    No Known Activations