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

    Neuronpedia

    INDEX
    Explanations

    code punctuations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cottage
    -0.07
     informal
    -0.07
     багатьох
    -0.07
     Ultimately
    -0.06
    posta
    -0.06
     cach
    -0.06
     těchto
    -0.06
    ukes
    -0.06
     cz
    -0.06
    logy
    -0.06
    POSITIVE LOGITS
     Thomson
    0.07
     Uri
    0.07
    _sphere
    0.07
    _di
    0.06
    树
    0.06
     uncommon
    0.06
     microtime
    0.06
    (docs
    0.06
    ONA
    0.06
     mView
    0.06
    Act Density 0.008%

    No Known Activations