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

    Neuronpedia

    INDEX
    Explanations

    frustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.24
     to
    1.02
    ни
    0.94
    не
    0.91
    м
    0.89
    ले
    0.87
    to
    0.85
    ται
    0.85
    다
    0.85
    ő
    0.80
    POSITIVE LOGITS
    s
    1.38
    a
    1.09
     vaccin
    0.98
    マ
    0.95
    ス
    0.94
     fiori
    0.90
     aviones
    0.89
    ส
    0.89
    药物
    0.87
     poziom
    0.86
    Act Density 0.005%

    No Known Activations