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

    Neuronpedia

    INDEX
    Explanations

    indicators of action and performance

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

    Followed by adverbs of manner

    np_acts-logits-general · gemini-2.0-flash

    actions done easily or with capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.68
     Taktlose
    -0.59
     propOrder
    -0.59
     الحره
    -0.58
    انيف
    -0.57
    ThroughAttribute
    -0.57
    новниш
    -0.55
     <=",
    -0.54
    ]=>
    -0.53
    #+#
    -0.51
    POSITIVE LOGITS
     fácilmente
    1.09
     facilmente
    0.96
     easily
    0.95
     facilement
    0.88
    ได้
    0.82
    easily
    0.80
     safely
    0.74
    媲
    0.70
     Easily
    0.65
    也可以
    0.65
    Act Density 0.579%

    No Known Activations