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

    Neuronpedia

    INDEX
    Explanations

    Generic statement terminator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    0.86
    F
    0.84
    N
    0.79
    B
    0.71
    Cafe
    0.70
    AR
    0.67
    E
    0.61
    0.60
    V
    0.60
    Germ
    0.60
    POSITIVE LOGITS
     சேர்த்து
    0.71
    на
    0.71
    磵
    0.71
    க
    0.70
    us
    0.68
    in
    0.67
    வற்ற
    0.66
    자
    0.66
     차량
    0.65
    ي
    0.65
    Act Density 0.003%

    No Known Activations