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

    Neuronpedia

    INDEX
    Explanations

    log probability calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.05
    𝐭
    0.88
    yc
    0.86
    𝐲
    0.85
     టీడీపీ
    0.85
     клуба
    0.83
     europea
    0.82
     europeo
    0.81
     финанси
    0.81
    ма
    0.81
    POSITIVE LOGITS
    >
    1.05
    潁
    0.98
    ização
    0.96
    gados
    0.95
    issä
    0.94
    嶂
    0.93
    р
    0.92
     adopters
    0.92
    で
    0.91
    er
    0.90
    Act Density 0.001%

    No Known Activations