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

    Neuronpedia

    INDEX
    Explanations

    code and data manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     원하는
    0.30
    水の
    0.30
     사용자
    0.30
     використання
    0.29
     رقم
    0.28
    水
    0.28
     மைய
    0.28
     під
    0.28
    特定の
    0.28
     לה
    0.28
    POSITIVE LOGITS
    at
    0.32
     wasn
    0.32
     haven
    0.31
    el
    0.30
    on
    0.30
    lan
    0.29
    ss
    0.29
    if
    0.29
    all
    0.28
    er
    0.27
    Act Density 0.186%

    No Known Activations