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

    Neuronpedia

    INDEX
    Explanations

    code/data/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chalk
    -0.07
    esub
    -0.06
    -ext
    -0.06
     gaps
    -0.06
     obsolete
    -0.06
    -level
    -0.06
    ayload
    -0.06
    �
    -0.06
    ד
    -0.06
    .Roll
    -0.06
    POSITIVE LOGITS
     carbohydrates
    0.08
     /\
    0.07
     lar
    0.07
    !$
    0.07
    ._↵
    0.06
     |:
    0.06
    chten
    0.06
    บาท
    0.06
     liberalism
    0.06
    ิร
    0.06
    Act Density 0.001%

    No Known Activations