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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and support for community efforts

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

    world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.45
     مرئيه
    -0.44
    lorette
    -0.43
    UIControlState
    -0.42
     <=",
    -0.41
    хьтан
    -0.39
    rinfo
    -0.38
     reta
    -0.38
     TextInput
    -0.38
     متعلقه
    -0.37
    POSITIVE LOGITS
     world
    1.45
    world
    1.28
     wereld
    1.13
    World
    1.13
     WORLD
    1.11
     mundo
    1.09
     World
    1.09
     worlds
    1.09
     düny
    1.05
    WORLD
    1.05
    Act Density 0.044%

    No Known Activations