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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and functions in code, particularly those that involve explaining procedures and outputting results

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

    reflexive verbs and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.72
    DockStyle
    -0.66
     المعيارى
    -0.62
    AnimationsModule
    -0.49
    Externé
    -0.48
    istoitu
    -0.48
    GEBURTSDATUM
    -0.48
    曖昧さ回避
    -0.47
    сылкі
    -0.47
    tvguidetime
    -0.47
    POSITIVE LOGITS
     sich
    0.48
     oneself
    0.43
    featureID
    0.42
     itself
    0.41
    izarse
    0.38
     themselves
    0.37
     widać
    0.36
     Yourself
    0.36
    idać
    0.36
     się
    0.36
    Act Density 0.005%

    No Known Activations