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

    Neuronpedia

    INDEX
    Explanations

    Horror stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [Byte
    -0.07
     stomach
    -0.07
    КА
    -0.06
     bear
    -0.06
    แล
    -0.06
    904
    -0.06
     Ton
    -0.06
     dear
    -0.06
     mapa
    -0.06
    Tags
    -0.06
    POSITIVE LOGITS
    <section
    0.06
    =localhost
    0.06
    .Google
    0.06
    :class
    0.06
    .Microsoft
    0.06
    adolu
    0.06
    _performance
    0.06
     갤
    0.06
     redevelopment
    0.06
    /favicon
    0.06
    Act Density 0.100%

    No Known Activations