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

    Neuronpedia

    INDEX
    Explanations

    radius volume calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buffs
    0.41
     rotund
    0.39
     synapses
    0.39
     emotes
    0.39
    आईओएस
    0.39
     spherical
    0.38
     giocatori
    0.38
     Biał
    0.37
     ricerc
    0.36
     pü
    0.36
    POSITIVE LOGITS
     Materials
    0.44
     Rail
    0.44
     Renewable
    0.39
    PERMISSION
    0.38
    楇
    0.37
     Controlling
    0.37
     circulating
    0.37
     Logs
    0.37
    媟
    0.36
     Rails
    0.36
    Act Density 0.006%

    No Known Activations