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

    Neuronpedia

    INDEX
    Explanations

    queue head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.82
    0
    0.59
    ’).
    0.59
    ς
    0.55
    ’:
    0.54
     Disorders
    0.53
    ’;
    0.53
     mensen
    0.50
     calendario
    0.49
    ’?
    0.49
    POSITIVE LOGITS
    ка
    0.66
    ك
    0.62
    скольку
    0.62
    u
    0.60
    на
    0.59
     efectuar
    0.58
    િ
    0.58
    quele
    0.56
     afectar
    0.54
    d
    0.52
    Act Density 0.203%

    No Known Activations