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

    Neuronpedia

    INDEX
    Explanations

    best suits or fits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꔰ
    0.43
     fuerzas
    0.41
     spoon
    0.41
     करू
    0.41
    骢
    0.40
     rayos
    0.39
    脑
    0.39
     custod
    0.37
     steeds
    0.37
    守护
    0.37
    POSITIVE LOGITS
    fi
    0.97
     фи
    0.95
     fi
    0.93
     fi
    0.82
    0.78
    fi
    0.74
     фі
    0.73
    フィ
    0.70
    фі
    0.68
    ფი
    0.68
    Act Density 0.015%

    No Known Activations