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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the price or difference of a topic

    oai_token-act-pair · gemini-2.0-flash

    different

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //
    -0.68
     rhestr
    -0.61
    뀜
    -0.61
    XmlAccessType
    -0.60
    
    -0.60
    oredCriteria
    -0.60
    DAOImpl
    -0.58
    ETIES
    -0.57
    /**
    -0.56
    뀐
    -0.56
    POSITIVE LOGITS
     different
    0.97
    Different
    0.95
    different
    0.93
     Different
    0.92
    other
    0.84
     diferente
    0.83
    Other
    0.82
     autre
    0.80
     differently
    0.80
     other
    0.79
    Act Density 0.745%

    No Known Activations