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

    Neuronpedia

    INDEX
    Explanations

    things that apply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [
    0.37
     tarz
    0.37
    ቧ
    0.36
     최대한
    0.36
     ক্যাম
    0.35
     Electoral
    0.34
     według
    0.34
    sai
    0.34
     为了
    0.33
     Residency
    0.33
    POSITIVE LOGITS
     applicable
    2.09
     applies
    2.00
    適用
    1.98
    applicable
    1.95
    适用于
    1.88
     Applicable
    1.86
     Applies
    1.82
     berlaku
    1.81
     applicability
    1.74
    适用
    1.69
    Act Density 0.064%

    No Known Activations