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

    Neuronpedia

    INDEX
    Explanations

    assembly .data section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tyrannical
    0.46
     extremist
    0.45
     insanely
    0.44
    warranty
    0.43
    חד
    0.42
     bombshell
    0.42
     insane
    0.41
     angry
    0.39
     ekstrem
    0.39
    startTime
    0.39
    POSITIVE LOGITS
     Descriptive
    0.41
     Beschreibung
    0.40
     Critique
    0.40
    类型的
    0.39
     제공
    0.39
     Computing
    0.38
     Beob
    0.38
     Distributions
    0.38
     വിവര
    0.38
     Studio
    0.38
    Act Density 0.001%

    No Known Activations