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

    Neuronpedia

    INDEX
    Explanations

    Colons in instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鉴
    -0.08
     bij
    -0.08
    bij
    -0.08
    数
    -0.07
     wings
    -0.07
     Alone
    -0.07
     കുടുംബ
    -0.07
    惊
    -0.07
     wing
    -0.07
     Teens
    -0.07
    POSITIVE LOGITS
     мора
    0.08
     попыт
    0.08
    は禁止
    0.08
     generell
    0.08
    hti
    0.08
    ierungen
    0.08
     inadvert
    0.08
     болон
    0.08
    etc
    0.08
     qab
    0.08
    Act Density 0.007%

    No Known Activations