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

    Neuronpedia

    INDEX
    Explanations

    physics and math

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apayati
    0.76
     IELTS
    0.75
    DeviceCompliance
    0.75
     showbiz
    0.73
     PUBG
    0.71
     Amnesty
    0.71
     palvel
    0.71
     صارفین
    0.71
     tiendas
    0.71
     Laravel
    0.70
    POSITIVE LOGITS
     finite
    0.80
     nonlinear
    0.80
     inhomogeneous
    0.80
     perturbation
    0.79
     coherent
    0.77
     nonlinearity
    0.76
     tractable
    0.76
     macroscopic
    0.75
     discretized
    0.75
     spatial
    0.74
    Act Density 0.082%

    No Known Activations