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

    Neuronpedia

    INDEX
    Explanations

    ability and inability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ान
    0.77
    sning
    0.64
    те
    0.58
    𝘀
    0.58
    ில்
    0.57
    ти
    0.57
    ys
    0.56
    αν
    0.55
    ේ
    0.54
    ים
    0.54
    POSITIVE LOGITS
    V
    0.79
    ﺩ
    0.61
     delights
    0.57
    F
    0.57
    Ꮻ
    0.57
    З
    0.57
    Ռ
    0.56
     Toen
    0.56
    Ве
    0.55
    Hãy
    0.55
    Act Density 0.537%

    No Known Activations