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

    Neuronpedia

    INDEX
    Explanations

    technical components and variables in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    detectChanges
    -0.42
     argint
    -0.40
    MENAFN
    -0.38
     žem
    -0.37
    addPreferredGap
    -0.36
     picioare
    -0.34
    ējās
    -0.34
     šķ
    -0.34
     Política
    -0.34
     Absch
    -0.33
    POSITIVE LOGITS
    verwijspagina
    0.52
     فريبيس
    0.51
    جوايز
    0.48
    slidesToShow
    0.47
    rungsseite
    0.47
    Története
    0.44
    intios
    0.44
     wireType
    0.42
    emlrt
    0.42
    asibility
    0.42
    Act Density 0.001%

    No Known Activations