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

    Neuronpedia

    INDEX
    Explanations

    Programming/technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boston
    -0.07
     lions
    -0.07
     cauliflower
    -0.06
     jumper
    -0.06
    (href
    -0.06
     jacket
    -0.06
     Gol
    -0.06
     polic
    -0.06
    enco
    -0.06
    最
    -0.06
    POSITIVE LOGITS
    πέ
    0.07
     příležit
    0.07
    dto
    0.07
    (format
    0.07
     lidé
    0.06
    Robert
    0.06
    ────
    0.06
     Reb
    0.06
    attrs
    0.06
    ubuntu
    0.06
    Act Density 0.019%

    No Known Activations