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

    Neuronpedia

    INDEX
    Explanations

    of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogenannten
    0.83
     sogenannte
    0.82
     berühm
    0.73
     cosidd
    0.73
     Großbritannien
    0.72
    வதற்காக
    0.71
     istilah
    0.70
     Gründung
    0.68
     வகையான
    0.68
     สถาน
    0.66
    POSITIVE LOGITS
    d
    0.70
    I
    0.70
    t
    0.68
    C
    0.66
    V
    0.66
    L
    0.65
    A
    0.63
    l
    0.62
    D
    0.62
    F
    0.61
    Act Density 0.000%

    No Known Activations