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

    Neuronpedia

    INDEX
    Explanations

    code, file handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiled
    -0.07
     หร
    -0.06
    (argument
    -0.06
    (am
    -0.06
    _extended
    -0.06
     �
    -0.06
     endanger
    -0.06
     EE
    -0.06
    _dispatch
    -0.06
    Wal
    -0.06
    POSITIVE LOGITS
     downloading
    0.07
     jersey
    0.06
     breasts
    0.06
     knock
    0.06
    ULO
    0.06
     documenting
    0.06
    RY
    0.06
    .append
    0.06
    DATE
    0.06
     Eston
    0.06
    Act Density 0.142%

    No Known Activations