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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and science fiction

    oai_token-act-pair · gemini-2.0-flash

    science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้อม
    -0.59
     sonore
    -0.47
     culoare
    -0.47
     immobilier
    -0.45
    NgModule
    -0.45
     Grau
    -0.44
     ſhe
    -0.44
     poème
    -0.44
     industriale
    -0.44
    poch
    -0.43
    POSITIVE LOGITS
    TagMode
    0.74
    MLLoader
    0.68
     betweenstory
    0.63
    titleMargin
    0.62
     <=",
    0.61
    writeFieldEnd
    0.60
    __':
    0.58
    withIdentifier
    0.58
    RegressionTest
    0.58
    Awal
    0.58
    Act Density 0.690%

    No Known Activations