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

    Neuronpedia

    INDEX
    Explanations

    player status when fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isc
    0.38
     යා
    0.38
    dec
    0.37
     dec
    0.37
     flick
    0.36
     mess
    0.35
     apasion
    0.35
     giants
    0.35
    quit
    0.35
    isci
    0.35
    POSITIVE LOGITS
     displacing
    0.55
     eligibility
    0.52
    Availability
    0.51
     फिट
    0.50
     starter
    0.49
    Starter
    0.49
     displ
    0.49
     availability
    0.48
    availability
    0.48
     cementing
    0.48
    Act Density 0.001%

    No Known Activations