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

    Neuronpedia

    INDEX
    Explanations

    recognition for achievements and efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.99
    ’
    0.75
    一
    0.74
    athe
    0.74
    ون
    0.73
    ת
    0.70
    '
    0.69
     out
    0.68
     Abortion
    0.68
    OM
    0.68
    POSITIVE LOGITS
    s
    0.81
    ll
    0.80
    ש
    0.78
    notlocked
    0.77
    mostrar
    0.77
     colorido
    0.76
    នៅលើ
    0.76
    ޏ
    0.76
     значи
    0.75
    n
    0.75
    Act Density 0.004%

    No Known Activations