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

    Neuronpedia

    INDEX
    Explanations

    empty or placeholder values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obso
    0.81
     badly
    0.79
     angry
    0.77
     TAR
    0.71
     nightmares
    0.70
     obsolete
    0.70
     horror
    0.70
    TAR
    0.69
     ತಪ್ಪ
    0.69
    ़
    0.69
    POSITIVE LOGITS
     रखें
    0.82
     هیچ
    0.82
     kecuali
    0.72
    gewicht
    0.72
     няма
    0.71
    即可
    0.70
    Placeholder
    0.70
    قاء
    0.70
    werten
    0.69
    ไม่มี
    0.69
    Act Density 1.029%

    No Known Activations