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

    Neuronpedia

    INDEX
    Explanations

    subjective feelings and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    0.85
     appetizing
    0.83
    kopf
    0.80
    gebaut
    0.80
    kosten
    0.79
    iato
    0.78
    kannya
    0.75
    k
    0.75
    ductor
    0.74
    kiej
    0.72
    POSITIVE LOGITS
    ↵
    1.03
     feelings
    0.72
    ар
    0.72
    ية
    0.70
    ز
    0.70
    ↵↵
    0.69
    其他
    0.65
    ;
    0.63
    al
    0.62
     de
    0.62
    Act Density 0.114%

    No Known Activations