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

    Neuronpedia

    INDEX
    Explanations

    programming errors and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shuffled
    -0.07
     brown
    -0.07
    Ranked
    -0.06
     happiness
    -0.06
     Gets
    -0.06
     nd
    -0.06
     sincere
    -0.06
     ness
    -0.06
     RET
    -0.06
     ماك
    -0.06
    POSITIVE LOGITS
     plasma
    0.07
    海
    0.07
    script
    0.07
    ΟΦ
    0.07
    ampled
    0.07
    _virtual
    0.06
    ups
    0.06
    .Dto
    0.06
    ỉ
    0.06
    lere
    0.06
    Act Density 0.000%

    No Known Activations