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

    Neuronpedia

    INDEX
    Explanations

    jungle environments and vibes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.64
    。
    0.63
    ामध्ये
    0.63
    ز
    0.60
    Ка
    0.59
    يا
    0.59
    اء
    0.59
    اق
    0.59
    و
    0.59
    εια
    0.59
    POSITIVE LOGITS
    at
    0.81
    ้
    0.69
    -
    0.63
     scrutin
    0.63
     agencies
    0.59
    ic
    0.59
     creatures
    0.59
     companies
    0.58
     beasts
    0.57
     r
    0.57
    Act Density 0.034%

    No Known Activations