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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fabric
    -0.07
    .Char
    -0.07
     styled
    -0.06
    ethyl
    -0.06
     scraped
    -0.06
    Launcher
    -0.06
    ampus
    -0.06
    <this
    -0.06
    _lab
    -0.06
    .En
    -0.06
    POSITIVE LOGITS
    願
    0.07
    有关
    0.07
     Howell
    0.06
    Identifier
    0.06
     echoes
    0.06
     embraces
    0.06
     Authenticate
    0.06
    番
    0.06
     сохра
    0.06
    撮
    0.06
    Act Density 0.006%

    No Known Activations