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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bur
    -0.07
    Wire
    -0.07
     Represent
    -0.06
    utches
    -0.06
    ضع
    -0.06
     Shields
    -0.06
     likely
    -0.06
     Holl
    -0.06
     yacc
    -0.06
     Rout
    -0.06
    POSITIVE LOGITS
     Baptist
    0.08
     ут
    0.07
     příro
    0.07
    vou
    0.06
     unlocked
    0.06
    験
    0.06
     채
    0.06
    鏡
    0.06
    ston
    0.06
     obec
    0.06
    Act Density 0.000%

    No Known Activations