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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comparaison
    0.71
     extré
    0.70
     epitome
    0.69
    زع
    0.69
     sétimo
    0.67
    část
    0.66
     continuar
    0.66
     lanjutan
    0.65
     handc
    0.65
     própri
    0.65
    POSITIVE LOGITS
     ρ
    1.95
     ϕ
    1.89
     θ
    1.80
     λ
    1.79
     σ
    1.78
     τ
    1.77
     x
    1.74
     p
    1.74
     ξ
    1.73
     δ
    1.72
    Act Density 0.359%

    No Known Activations