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

    Neuronpedia

    INDEX
    Explanations

    getting started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ler
    0.71
    land
    0.65
    center
    0.65
    ↵
    0.63
    to
    0.59
     to
    0.59
    ell
    0.55
    hat
    0.54
    ok
    0.53
    ner
    0.53
    POSITIVE LOGITS
     faiblement
    0.62
     mè
    0.58
    प
    0.57
     thermique
    0.55
     clumps
    0.55
    ડ
    0.54
    ブ
    0.54
     roam
    0.53
     demean
    0.51
    ச
    0.51
    Act Density 0.556%

    No Known Activations