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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a response or action relating to a specific event or situation

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

    location or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pouvoit
    -0.51
    waitKey
    -0.48
    новништво
    -0.45
     lendemain
    -0.45
    Revenir
    -0.45
     velours
    -0.45
     čierna
    -0.44
    __((
    -0.44
     auroit
    -0.44
     caneca
    -0.43
    POSITIVE LOGITS
     مرئيه
    0.49
    hangi
    0.38
    절
    0.38
    fromnode
    0.37
     Cata
    0.37
    Intra
    0.36
     sarili
    0.36
    ghum
    0.36
     Эк
    0.35
    Tc
    0.35
    Act Density 0.110%

    No Known Activations