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

    Neuronpedia

    INDEX
    Explanations

    growing field and body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    disabled
    0.52
    ool
    0.49
    Opt
    0.48
    ter
    0.48
    lás
    0.48
    scr
    0.48
    Generic
    0.48
    körper
    0.47
    lt
    0.47
    opt
    0.47
    POSITIVE LOGITS
     of
    0.48
     Curie
    0.47
     dove
    0.46
     violently
    0.45
     fluorine
    0.45
     perfettamente
    0.44
     ranking
    0.44
     attacking
    0.43
     delight
    0.42
     tongue
    0.42
    Act Density 0.000%

    No Known Activations