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

    Neuronpedia

    INDEX
    Explanations

    blocking mechanism strength directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ؟!
    0.49
     громадян
    0.47
    핼
    0.45
    ?!?!
    0.43
    ட்டி
    0.43
     ауто
    0.43
     очередной
    0.43
    гада
    0.43
    Гор
    0.43
    ርዓ
    0.43
    POSITIVE LOGITS
     it
    0.59
     only
    0.57
    t
    0.52
    it
    0.50
    ia
    0.50
    id
    0.48
     its
    0.48
     die
    0.46
    ms
    0.45
     It
    0.44
    Act Density 0.002%

    No Known Activations