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

    Neuronpedia

    INDEX
    Explanations

    celda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administratif
    0.88
     Süd
    0.87
     poderia
    0.86
     Unterschied
    0.86
     serviço
    0.85
     novo
    0.84
     político
    0.84
     verschiedenen
    0.83
     strait
    0.82
    nuevo
    0.82
    POSITIVE LOGITS
    uc
    0.91
    ل
    0.85
    徜
    0.79
    oc
    0.77
    телно
    0.77
    a
    0.76
    ar
    0.75
    uk
    0.74
    ud
    0.70
    ill
    0.70
    Act Density 0.000%

    No Known Activations