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

    Neuronpedia

    INDEX
    Explanations

    the prefix "pro"

    oai_token-act-pair · gemini-2.0-flash

    pro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.75
     kasarigan
    -0.64
    writerow
    -0.61
     مشين
    -0.61
     باخ
    -0.59
     >=",
    -0.57
     continúas
    -0.56
     nakalista
    -0.54
    LLocation
    -0.54
    IonicModule
    -0.53
    POSITIVE LOGITS
     Universitaria
    0.63
     Económica
    0.54
     affari
    0.53
     alimentaires
    0.51
     fondi
    0.50
     religieuses
    0.50
     applicazioni
    0.48
     traseiro
    0.48
     académico
    0.47
     équipements
    0.47
    Act Density 0.314%

    No Known Activations