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

    Neuronpedia

    INDEX
    Explanations

    crisis, genuine, boring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ЛЕ
    0.87
    តា
    0.80
    ﺢ
    0.80
    РЕ
    0.80
    QUA
    0.79
    ﺵ
    0.79
     quasi
    0.78
    ᅣ
    0.76
     qa
    0.76
     Jura
    0.75
    POSITIVE LOGITS
    astype
    0.98
    ativer
    0.97
     earthqu
    0.94
    ighth
    0.92
    querysearch
    0.92
    passt
    0.90
    permissionid
    0.89
     undert
    0.89
    arget
    0.88
    userid
    0.87
    Act Density 0.233%

    No Known Activations