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

    Neuronpedia

    INDEX
    Explanations

    Express or implied warranties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nymphs
    0.38
    秙
    0.38
    ྪ
    0.37
     végétation
    0.37
    க்ஸாண்ட
    0.37
     diaphr
    0.37
    اردوش
    0.36
    addassa
    0.36
     ശരീര
    0.35
     rétréci
    0.34
    POSITIVE LOGITS
    0.45
     "
    0.44
    E
    0.41
    ↵
    0.38
    w
    0.37
    !
    0.37
    Ex
    0.37
    P
    0.36
    N
    0.36
    EM
    0.35
    Act Density 0.001%

    No Known Activations