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

    Neuronpedia

    INDEX
    Explanations

    within

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cação
    -0.07
     tekst
    -0.07
     TESTING
    -0.07
    タル
    -0.07
    畏惧
    -0.07
    นอกจาก
    -0.06
     ככה
    -0.06
     prefix
    -0.06
    鲹
    -0.06
     trillion
    -0.06
    POSITIVE LOGITS
    Erot
    0.07
     SOUR
    0.07
    小姐
    0.07
    ToEnd
    0.07
    chez
    0.07
    ("#{
    0.07
    Respons
    0.07
    לקוח
    0.07
     Correspond
    0.06
     shrugged
    0.06
    Act Density 0.000%

    No Known Activations