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

    Neuronpedia

    INDEX
    Explanations

    footnotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Named
    -0.07
    Б
    -0.07
     возраст
    -0.06
    face
    -0.06
     coisa
    -0.06
     thou
    -0.06
     knowledge
    -0.06
    @include
    -0.06
     place
    -0.06
    NG
    -0.06
    POSITIVE LOGITS
     осві
    0.07
     sağlamak
    0.06
    .InnerException
    0.06
     puta
    0.06
    -sm
    0.06
    Runtime
    0.06
    ać
    0.06
    ॉर
    0.06
    -sk
    0.06
     okhttp
    0.06
    Act Density 0.005%

    No Known Activations