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

    Neuronpedia

    INDEX
    Explanations

    programming references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jackman
    1.35
    kut
    1.26
    hor
    1.18
    Jack
    1.17
    wax
    1.16
     Maher
    1.16
     Hough
    1.15
    pian
    1.10
    husband
    1.09
    warts
    1.09
    POSITIVE LOGITS
    ref
    1.13
     Ref
    1.13
     ref
    1.04
    Ref
    1.01
    REF
    1.01
     REF
    0.97
     firebase
    0.88
    RefManager
    0.82
    RefSet
    0.74
     réf
    0.73
    Act Density 1.781%

    No Known Activations