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

    Neuronpedia

    INDEX
    Explanations

    phrases related to floating or lifting objects

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

    levitating, floating, lifted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    angliski
    -0.57
    ImageContext
    -0.56
     náv
    -0.56
    gameserver
    -0.50
     menyal
    -0.47
     Administrativna
    -0.47
    pexpr
    -0.45
     billede
    -0.45
    ersachsen
    -0.44
    věd
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.54
    lift
    0.45
     lift
    0.43
    Lift
    0.40
     Lift
    0.38
    LookAnd
    0.38
     Feedback
    0.38
    lifted
    0.37
     lifted
    0.36
     hovering
    0.36
    Act Density 0.087%

    No Known Activations