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

    Neuronpedia

    INDEX
    Explanations

    limit and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    besar
    0.56
    charges
    0.55
    δη
    0.54
     instituições
    0.54
    δια
    0.53
    బ్బు
    0.53
    ciaux
    0.52
    大
    0.52
    비
    0.52
    તે
    0.51
    POSITIVE LOGITS
     limited
    1.13
     limit
    1.09
     सीमित
    1.09
     제한
    1.06
     محدود
    1.05
     limiting
    1.02
     Limited
    1.01
     limitar
    1.01
     limité
    1.00
     Limit
    0.99
    Act Density 0.189%

    No Known Activations