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

    Neuronpedia

    INDEX
    Explanations

    specific items and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destruir
    0.41
     craz
    0.40
    vidia
    0.40
    endeu
    0.40
     سات
    0.38
     desiderio
    0.38
     mieux
    0.37
     měst
    0.37
    ništva
    0.37
     করেনি
    0.37
    POSITIVE LOGITS
    珢
    0.42
    "};
    0.41
    Feels
    0.40
     Engaging
    0.37
     Най
    0.37
    强者
    0.36
     հետ
    0.36
    Engagement
    0.36
    浯
    0.36
     Respons
    0.35
    Act Density 0.000%

    No Known Activations