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

    Neuronpedia

    INDEX
    Explanations

    report an accident, introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ficando
    0.87
     médias
    0.82
    ки
    0.81
    吗
    0.79
    經歷
    0.77
     энциклопедия
    0.76
     mágico
    0.75
    0.74
     μέσα
    0.73
     içinde
    0.73
    POSITIVE LOGITS
    ቖ
    0.72
    ari
    0.70
     truc
    0.67
     Thirteen
    0.66
     LIABLE
    0.66
     Guarant
    0.65
     beef
    0.64
    Doug
    0.64
     Beef
    0.63
    𝙿
    0.63
    Act Density 0.001%

    No Known Activations