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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to increases or doubling in quantity or value

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

    doubling and halving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MotionEvent
    -0.40
     teclas
    -0.39
    >//
    -0.35
    ="\
    -0.34
     court
    -0.33
     Económica
    -0.33
     отметить
    -0.32
     Court
    -0.32
     céramique
    -0.32
    __":
    -0.32
    POSITIVE LOGITS
    RTGC
    0.78
    хьтан
    0.78
     doubling
    0.78
     doubled
    0.72
     Doub
    0.68
    tagHelperRunner
    0.67
    postsleuth
    0.65
    expandindo
    0.65
     Doubles
    0.65
    #+#
    0.64
    Act Density 0.016%

    No Known Activations