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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.72
    twimg
    -0.66
    قایناقلار
    -0.63
    parsedMessage
    -0.58
     EnglishChoose
    -0.57
     Census
    -0.55
    evos
    -0.54
    (;;)
    -0.50
     umani
    -0.49
    Enllaces
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.54
    Carriera
    0.51
    逅
    0.50
    ритори
    0.49
    WebElementEntity
    0.48
     divulgação
    0.47
    essoal
    0.47
    HORE
    0.47
    ériale
    0.47
     execução
    0.44
    Act Density 0.031%

    No Known Activations