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

    Neuronpedia

    INDEX
    Explanations

    function evaluation f(x)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ؛
    0.87
    ;
    0.80
     intereses
    0.78
     internazionali
    0.76
     gehad
    0.74
    );
    0.73
     interessi
    0.71
     povos
    0.71
     credito
    0.70
     judiciales
    0.70
    POSITIVE LOGITS
     वैशिष्ट
    0.67
    ₁(
    0.65
    ρ
    0.64
    探
    0.61
     Fourier
    0.60
    여기
    0.59
    density
    0.58
    ър
    0.58
    мір
    0.57
    ळख
    0.57
    Act Density 0.008%

    No Known Activations