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

    Neuronpedia

    INDEX
    Explanations

    after sequence following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buiten
    0.88
     éve
    0.86
     экономи
    0.79
     不过
    0.78
     наиболее
    0.77
     compañías
    0.76
     ngoại
    0.75
     применя
    0.75
     adelant
    0.75
     gezegd
    0.74
    POSITIVE LOGITS
    G
    0.83
    as
    0.82
    L
    0.80
    N
    0.79
    R
    0.73
    า
    0.72
    ال
    0.72
    Text
    0.71
    сток
    0.70
    P
    0.70
    Act Density 0.002%

    No Known Activations