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

    Neuronpedia

    INDEX
    Explanations

    aftercare, genes, crush, pain, county

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    N
    0.61
    O
    0.60
    T
    0.58
    W
    0.56
    U
    0.54
    D
    0.52
    F
    0.52
    ut
    0.52
    ew
    0.50
    ate
    0.50
    POSITIVE LOGITS
    은
    0.58
    ورسٹی
    0.57
     idealism
    0.55
    ከሰ
    0.55
     ت
    0.54
    昰
    0.52
    는
    0.52
     ی
    0.51
     outta
    0.51
     нему
    0.50
    Act Density 0.000%

    No Known Activations