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

    Neuronpedia

    INDEX
    Explanations

    We propose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     змо
    0.90
    ية
    0.89
    வர்க
    0.85
     lysosomes
    0.84
     excitatory
    0.83
     diagonalizable
    0.83
    getNome
    0.83
     Inorg
    0.83
     lysis
    0.82
    (../
    0.81
    POSITIVE LOGITS
    ект
    0.76
    d
    0.74
    עות
    0.73
    ellent
    0.72
    κος
    0.71
    ➢
    0.71
    ホーム
    0.70
    ায়
    0.70
    主に
    0.69
    ouwd
    0.69
    Act Density 0.001%

    No Known Activations