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

    Neuronpedia

    INDEX
    Explanations

    help or assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     모습
    -0.07
    _Red
    -0.07
     oral
    -0.06
    per
    -0.06
    ']↵↵↵
    -0.06
    _Metadata
    -0.06
    .Observer
    -0.06
    last
    -0.06
    .Argument
    -0.06
    TreeNode
    -0.06
    POSITIVE LOGITS
    -gradient
    0.07
     (((
    0.07
    得
    0.06
    ritic
    0.06
     Spr
    0.06
     Gott
    0.06
    ışı
    0.06
     東
    0.06
    щие
    0.06
     freaking
    0.06
    Act Density 0.019%

    No Known Activations