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

    Neuronpedia

    INDEX
    Explanations

    cultural revival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     persönlichen
    0.44
    shower
    0.42
    आपको
    0.42
     విషయ
    0.41
    外界
    0.40
    uc
    0.39
    겠습니다
    0.39
     возника
    0.39
    Ard
    0.39
    ርስ
    0.38
    POSITIVE LOGITS
     undead
    0.46
     bloque
    0.45
     enough
    0.44
     voisins
    0.44
     deja
    0.43
     setzt
    0.43
     plaid
    0.42
     jugó
    0.42
     ủng
    0.42
     Tó
    0.42
    Act Density 0.013%

    No Known Activations