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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to health and treatment efficacy

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

    complete recovery or reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.76
     المعيارى
    -0.66
     NSCoder
    -0.65
     lenker
    -0.61
    Autoritní
    -0.61
    CppMethod
    -0.60
    bootstrapcdn
    -0.59
    GEBURTSDATUM
    -0.59
    fjspx
    -0.58
    ConstraintMaker
    -0.57
    POSITIVE LOGITS
     dropped
    0.38
     aggressive
    0.37
    HT
    0.35
     hostile
    0.35
     nasty
    0.34
     inappropriate
    0.34
     violent
    0.34
     keli
    0.33
     unwanted
    0.33
    ht
    0.32
    Act Density 0.071%

    No Known Activations