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

    Neuronpedia

    INDEX
    Explanations

    arsenic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    2.75
    er
    2.62
    ת
    2.57
    a
    2.28
    ০
    2.17
    es
    2.16
    ್
    2.05
    д
    2.04
    et
    2.03
    al
    2.03
    POSITIVE LOGITS
     chắn
    1.74
    ানি
    1.60
    LE
    1.60
    democracy
    1.58
    Supplementary
    1.56
     Ceci
    1.56
    newer
    1.54
    acijos
    1.50
     aprob
    1.50
    MACl
    1.49
    Act Density 0.000%

    No Known Activations