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

    Neuronpedia

    INDEX
    Explanations

    names with titles and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immutable
    0.23
     vassals
    0.23
     CPUs
    0.22
     undead
    0.22
     infl
    0.21
     naught
    0.21
     epochs
    0.21
     illusory
    0.21
     granularity
    0.21
     bloques
    0.21
    POSITIVE LOGITS
    а
    0.28
    с
    0.27
    렌
    0.27
    ४
    0.27
    코
    0.27
    िया
    0.26
    িস
    0.25
    J
    0.25
    Н
    0.25
    নি
    0.24
    Act Density 0.047%

    No Known Activations