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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poner
    -0.07
    .bridge
    -0.06
    910
    -0.06
     Currently
    -0.06
     какой
    -0.06
     Nancy
    -0.06
     esl
    -0.06
     naveg
    -0.06
     aku
    -0.06
     mana
    -0.06
    POSITIVE LOGITS
    TAG
    0.07
     Ord
    0.06
    ату
    0.06
    ат
    0.06
     секрет
    0.06
    irst
    0.06
     подум
    0.06
    _SECRET
    0.06
    ‌کند
    0.06
    otionEvent
    0.06
    Act Density 0.000%

    No Known Activations