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

    Neuronpedia

    INDEX
    Explanations

    parentheses and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TreeNode
    -0.07
     Believe
    -0.07
    ibaba
    -0.06
     Tỉnh
    -0.06
     hilarious
    -0.06
     Rolling
    -0.06
     Melania
    -0.06
     остав
    -0.06
    <Comment
    -0.06
     TAS
    -0.06
    POSITIVE LOGITS
    (edge
    0.07
    �
    0.07
     intimate
    0.07
    .art
    0.06
     şüph
    0.06
    UNS
    0.06
    解决
    0.06
    erti
    0.06
     그녀
    0.06
     HE
    0.06
    Act Density 0.016%

    No Known Activations