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

    Neuronpedia

    INDEX
    Explanations

    timed out, for recipient or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पुरंदरे
    0.52
     Luxurious
    0.52
     Cheetah
    0.52
     Tendulkar
    0.51
     Politik
    0.50
     Stadium
    0.50
     అనంతరం
    0.50
     Crunchy
    0.50
    adakan
    0.50
     Stupid
    0.50
    POSITIVE LOGITS
     pools
    0.48
     modified
    0.47
     welfare
    0.45
     estacion
    0.44
     chain
    0.44
     stars
    0.44
     flows
    0.44
    0.44
     rays
    0.43
     diagnosis
    0.43
    Act Density 0.001%

    No Known Activations