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

    Neuronpedia

    INDEX
    Explanations

    internet text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ASC
    -0.07
     官
    -0.07
     Catholic
    -0.07
     Kn
    -0.07
     clutter
    -0.06
     AES
    -0.06
    ersistence
    -0.06
     Percent
    -0.06
     zal
    -0.06
    .Man
    -0.06
    POSITIVE LOGITS
    iphone
    0.06
     Alaska
    0.06
    ρο
    0.06
     Prelude
    0.06
     fase
    0.06
    atego
    0.06
    entin
    0.06
    _zone
    0.06
    fans
    0.06
    .deb
    0.06
    Act Density 0.016%

    No Known Activations