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

    Neuronpedia

    INDEX
    Explanations

    adoration, appreciation, worthiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cyg
    0.40
     టా
    0.39
     Ceres
    0.39
    RangeException
    0.37
    控制
    0.37
     perform
    0.36
    argmin
    0.36
    perform
    0.36
     Midwestern
    0.35
     USC
    0.34
    POSITIVE LOGITS
     благоприят
    0.39
     appreciation
    0.38
    價值
    0.38
    worthiness
    0.38
     adoration
    0.37
     affectionate
    0.36
    价值
    0.35
     mortgages
    0.35
     adore
    0.35
    ناك
    0.35
    Act Density 0.002%

    No Known Activations