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

    Neuronpedia

    INDEX
    Explanations

    news questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lycodon
    0.86
     sämt
    0.85
     dosimetry
    0.83
    라도
    0.83
     verwendeten
    0.83
    ,【
    0.82
    の状態
    0.82
    ၊
    0.81
     utilizados
    0.81
    に使用
    0.81
    POSITIVE LOGITS
    ningen
    0.93
    ah
    0.92
    amiento
    0.89
    ned
    0.87
    oting
    0.86
     ballroom
    0.86
    ahorse
    0.83
    d
    0.83
    utan
    0.80
    anam
    0.79
    Act Density 0.006%

    No Known Activations