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

    Neuronpedia

    INDEX
    Explanations

    code or scripting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transmission
    -0.07
    —the
    -0.07
    _future
    -0.06
    .Activity
    -0.06
     Shield
    -0.06
    fighters
    -0.06
    ーニ
    -0.06
    Fair
    -0.06
     Brunswick
    -0.06
     palabras
    -0.06
    POSITIVE LOGITS
     sexy
    0.07
     instructed
    0.06
    IENT
    0.06
     千
    0.06
    跟
    0.06
    readcr
    0.06
     fem
    0.06
     gloss
    0.06
     cath
    0.06
     SimpleDateFormat
    0.06
    Act Density 0.000%

    No Known Activations