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

    Neuronpedia

    INDEX
    Explanations

    Nagoya

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilevel
    0.41
    oxine
    0.40
     Marseille
    0.39
    swiss
    0.38
     equipo
    0.37
     מספר
    0.37
    swa
    0.37
     calc
    0.36
     Pensacola
    0.36
     PPM
    0.36
    POSITIVE LOGITS
    Cov
    0.53
     Coventry
    0.41
     Warwickshire
    0.40
     Cov
    0.40
    writeValue
    0.39
    纫
    0.39
    covariance
    0.38
     заместитель
    0.38
    Dimension
    0.37
    barkeit
    0.37
    Act Density 0.000%

    No Known Activations