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

    Neuronpedia

    INDEX
    Explanations

    opposite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cond
    -0.07
     drawable
    -0.07
    htags
    -0.06
     decals
    -0.06
     volcan
    -0.06
     mech
    -0.06
    タイ
    -0.06
     drone
    -0.06
     withd
    -0.06
     travers
    -0.06
    POSITIVE LOGITS
     opposite
    0.21
    @example
    0.08
    _done
    0.07
    expected
    0.07
     Copy
    0.07
    <Project
    0.07
     mosaic
    0.07
    andidate
    0.06
    _payload
    0.06
    .pb
    0.06
    Act Density 0.003%

    No Known Activations