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

    Neuronpedia

    INDEX
    Explanations

    default passwords and credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิ
    0.47
    ى
    0.47
    т
    0.47
    ֆ
    0.46
    ispiele
    0.46
    бла
    0.46
     뜻
    0.46
     자세
    0.46
    фу
    0.45
     ദി
    0.45
    POSITIVE LOGITS
     during
    0.57
     of
    0.52
     to
    0.50
    during
    0.49
     embarking
    0.49
     when
    0.47
     at
    0.47
    4
    0.46
     embark
    0.45
     houses
    0.45
    Act Density 0.012%

    No Known Activations