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

    Neuronpedia

    INDEX
    Explanations

    Amazon URLs and ISBNs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Providence
    -0.06
    ってい
    -0.06
    _parse
    -0.06
     Katz
    -0.06
    네
    -0.06
    ColumnInfo
    -0.06
    Profile
    -0.06
    χε
    -0.06
     وس
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     splitter
    0.07
    gabe
    0.07
    ashington
    0.07
     wirklich
    0.07
     ⓘ
    0.07
    gra
    0.06
    -package
    0.06
     darken
    0.06
    assage
    0.06
    allows
    0.06
    Act Density 0.005%

    No Known Activations