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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lesser
    -0.08
    filer
    -0.07
     blogger
    -0.07
     �
    -0.07
     theories
    -0.07
     aggregator
    -0.07
    Noise
    -0.06
     гр
    -0.06
     Blender
    -0.06
    _SWAP
    -0.06
    POSITIVE LOGITS
     amusing
    0.06
    �
    0.06
    isset
    0.06
     '}↵
    0.06
     Diabetes
    0.06
    endphp
    0.06
    如
    0.06
    .:.:.:.:.:.:.:.:
    0.06
    ักษ
    0.06
    (point
    0.06
    Act Density 0.121%

    No Known Activations