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

    Neuronpedia

    INDEX
    Explanations

    documentation comments with tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.05
    I
    0.93
    ت
    0.85
    त
    0.79
    ת
    0.79
    ST
    0.73
    IC
    0.72
    ل
    0.72
    transistors
    0.71
    IG
    0.71
    POSITIVE LOGITS
     attract
    0.77
    ’
    0.74
     obstructed
    0.72
     contribute
    0.71
     obliterated
    0.71
    স
    0.70
     ensue
    0.66
     safeguard
    0.65
     in
    0.65
     colectivo
    0.65
    Act Density 0.001%

    No Known Activations