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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ʱ
    -0.08
     Goth
    -0.07
     Ye
    -0.07
     require
    -0.07
    ánh
    -0.07
    �
    -0.07
    שמן
    -0.07
     Domino
    -0.07
    Say
    -0.06
    Sweet
    -0.06
    POSITIVE LOGITS
    闵
    0.07
    isChecked
    0.07
     vườ
    0.07
    更快
    0.07
     mediocre
    0.07
    .seconds
    0.07
    חינ
    0.07
    新材料
    0.06
    .RegisterType
    0.06
    对未来
    0.06
    Act Density 0.174%

    No Known Activations