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

    Neuronpedia

    INDEX
    Explanations

    references to episodes and narratives within a series or text

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

    previously tested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.43
    ########.
    -0.43
     šķ
    -0.40
     المعيارى
    -0.39
    insics
    -0.38
    colgante
    -0.36
     विश्वसनीयता
    -0.36
    envolvimento
    -0.35
    fak
    -0.35
    脚注の使い方
    -0.34
    POSITIVE LOGITS
    sidemargin
    0.55
    setViewportView
    0.48
    Попис
    0.47
     useAppContext
    0.47
    InputBorder
    0.46
    addPreferredGap
    0.46
     ſche
    0.45
    flashdata
    0.45
    basicConfig
    0.44
     typelib
    0.44
    Act Density 0.063%

    No Known Activations