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

    Neuronpedia

    INDEX
    Explanations

    code, commands, and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.56
    al
    0.55
    u
    0.53
     P
    0.52
    ia
    0.52
    ontium
    0.51
    ol
    0.50
    ain
    0.50
     to
    0.50
    ian
    0.49
    POSITIVE LOGITS
    Eres
    0.62
    Prés
    0.61
    Leadership
    0.54
    Ricardo
    0.54
     カバー
    0.54
    大
    0.53
     Мини
    0.53
    Tema
    0.52
    Lovely
    0.52
    Nashville
    0.51
    Act Density 0.000%

    No Known Activations