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

    Neuronpedia

    INDEX
    Explanations

    other protected characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estoque
    0.47
     aparel
    0.44
     steric
    0.44
     pretzels
    0.44
    و
    0.43
     haci
    0.42
    แต่
    0.42
     aulas
    0.41
     be
    0.41
     wages
    0.41
    POSITIVE LOGITS
    in
    0.84
    ap
    0.73
    я
    0.69
    x
    0.65
    s
    0.64
    اک
    0.62
    h
    0.60
    at
    0.59
    в
    0.58
    up
    0.57
    Act Density 0.404%

    No Known Activations