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

    Neuronpedia

    INDEX
    Explanations

    python logging formatters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nine
    0.91
     eight
    0.87
     one
    0.85
     nueve
    0.80
     connotations
    0.79
     hilar
    0.78
     dunque
    0.76
     connotation
    0.76
    one
    0.75
     mío
    0.74
    POSITIVE LOGITS
     Box
    0.95
    業務用
    0.90
    OC
    0.86
     Boxes
    0.86
    国際
    0.85
     BOX
    0.84
     ṣe
    0.83
     box
    0.81
    Box
    0.80
     Oc
    0.80
    Act Density 0.021%

    No Known Activations