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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å®ł
    -0.27
     ser
    -0.26
     externally
    -0.26
    寵
    -0.26
    å¤ĩ
    -0.25
    neh
    -0.24
     renamed
    -0.24
    éĽĩ
    -0.24
    oke
    -0.24
    认
    -0.23
    POSITIVE LOGITS
     Hansen
    0.31
    dice
    0.28
     indices
    0.28
     Indices
    0.28
    ç®Ń
    0.26
    arias
    0.25
     PHI
    0.25
    indices
    0.25
    (indices
    0.25
    pivot
    0.24
    Act Density 0.073%

    No Known Activations