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

    Neuronpedia

    INDEX
    Explanations

    Darcy, Harappa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    им
    0.85
    at
    0.79
    for
    0.79
    '
    0.78
    this
    0.77
    the
    0.76
    ім
    0.76
    A
    0.76
    ровали
    0.74
    a
    0.74
    POSITIVE LOGITS
     de
    0.80
     in
    0.69
    માં
    0.65
    的
    0.65
     tegen
    0.63
    的其他
    0.63
     stehen
    0.63
     मुनाफा
    0.62
     nebude
    0.62
    Request
    0.61
    Act Density 0.000%

    No Known Activations