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

    Neuronpedia

    INDEX
    Explanations

    The neuron seems to be identifying the beginning of sentences and/or some markdown formatting

    oai_token-act-pair · gemini-2.0-flash

    "//"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.66
     Obrador
    -0.61
    tanleria
    -0.58
    ंदीखरीदारी
    -0.57
    DockStyle
    -0.56
    TRIBUN
    -0.55
     Enix
    -0.53
     trajets
    -0.52
    RegistryLite
    -0.51
     getchar
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.60
     raiſ
    0.59
    ScopeManager
    0.58
    uxxxx
    0.57
    <bos>
    0.57
     morales
    0.56
     AppColors
    0.54
    antaranya
    0.53
     Sito
    0.52
    Portail
    0.51
    Act Density 1.132%

    No Known Activations