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

    Neuronpedia

    INDEX
    Explanations

    code and configuration properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    说法
    0.44
    Porque
    0.42
    accompagn
    0.41
    uzioni
    0.41
    Questa
    0.41
    {\"
    0.40
     fatig
    0.40
     দৃশ
    0.40
    };
    0.39
    Afrique
    0.39
    POSITIVE LOGITS
    reth
    0.48
    m
    0.43
    هن
    0.42
    mixed
    0.41
    的情
    0.41
    ו
    0.41
    mer
    0.40
     rooster
    0.40
    颔
    0.40
    mixing
    0.39
    Act Density 0.000%

    No Known Activations