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

    Neuronpedia

    INDEX
    Explanations

    restate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nity
    0.39
     Remark
    0.38
     verr
    0.38
    Flare
    0.38
    ism
    0.37
    性に
    0.37
    flags
    0.35
     remark
    0.35
    Tech
    0.35
    curl
    0.35
    POSITIVE LOGITS
    *}{
    0.59
    *}
    0.57
    *}$
    0.50
     *}
    0.49
     unlabeled
    0.49
     ''){
    0.48
     summarize
    0.47
     summarise
    0.46
     *}\
    0.46
     phrasing
    0.45
    Act Density 0.001%

    No Known Activations