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

    Neuronpedia

    INDEX
    Explanations

    movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simulation
    -0.07
    vanished
    -0.07
     CHILD
    -0.06
     Manhattan
    -0.06
    ün
    -0.06
     drill
    -0.06
    Market
    -0.06
     charitable
    -0.06
     german
    -0.06
    GB
    -0.06
    POSITIVE LOGITS
     *));↵
    0.06
    .intValue
    0.06
     shipments
    0.06
    -read
    0.06
     crunch
    0.06
    .getStatusCode
    0.06
    .GetFiles
    0.06
    atri
    0.06
     LEFT
    0.06
    Anal
    0.06
    Act Density 0.031%

    No Known Activations