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

    Neuronpedia

    INDEX
    Explanations

    mentions of methodologies or techniques

    oai_token-act-pair · gemini-2.0-flash

    Methods and techniques

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.50
     itself
    -0.49
     alone
    -0.46
     herv
    -0.46
     certainly
    -0.46
    
    -0.46
     practise
    -0.46
    iga
    -0.45
     Teams
    -0.45
    lione
    -0.44
    POSITIVE LOGITS
     onCreateView
    0.82
    expandindo
    0.69
    //});
    0.64
    AndEndTag
    0.63
     fallu
    0.61
     condamné
    0.60
    ConverterFactory
    0.60
    awaiter
    0.58
     للاسماء
    0.58
     couverte
    0.57
    Act Density 0.662%

    No Known Activations