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

    Neuronpedia

    INDEX
    Explanations

    try

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ือ
    -0.07
    "]:
    -0.07
    entina
    -0.07
    ْ
    -0.07
    日报道
    -0.07
    硐
    -0.06
    موقع
    -0.06
    Sept
    -0.06
    画面
    -0.06
    אוה
    -0.06
    POSITIVE LOGITS
     Bast
    0.08
     Dating
    0.07
     needs
    0.06
     tidy
    0.06
     concaten
    0.06
     far
    0.06
    成本
    0.06
    staking
    0.06
     movie
    0.06
    쟁
    0.06
    Act Density 0.002%

    No Known Activations