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

    Neuronpedia

    INDEX
    Explanations

    mammals and mammalian concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    3.39
    ون
    2.09
    يف
    2.05
    ě
    1.95
     phép
    1.77
    ţie
    1.77
     μόνο
    1.74
    াউন
    1.73
    يتي
    1.73
    ви
    1.70
    POSITIVE LOGITS
    ৫
    2.58
    t
    2.28
    ৮
    2.16
    いです
    2.03
     littered
    2.02
    ب
    1.99
    tio
    1.98
    ৭
    1.95
    нку
    1.86
    theless
    1.83
    Act Density 0.058%

    No Known Activations