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

    Neuronpedia

    INDEX
    Explanations

    gerrymandering, cherry-picking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.16
    1
    0.89
    S
    0.89
    as
    0.79
    7
    0.77
    an
    0.77
    P
    0.75
    3
    0.74
    6
    0.72
    es
    0.72
    POSITIVE LOGITS
    ابہ
    0.58
    朧
    0.57
     vrata
    0.55
     त्य
    0.55
     Selasa
    0.55
     tulis
    0.55
    toctree
    0.54
     urmă
    0.54
     relato
    0.54
     njih
    0.53
    Act Density 0.000%

    No Known Activations