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

    Neuronpedia

    INDEX
    Explanations

    references to presence and location

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

    where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vidite
    -0.48
     Balance
    -0.48
     kaarangay
    -0.47
    Yor
    -0.47
    руйте
    -0.44
    Blade
    -0.43
     sod
    -0.43
     Blade
    -0.42
    充
    -0.42
    Balance
    -0.41
    POSITIVE LOGITS
     Allí
    0.79
     where
    0.78
     acolo
    0.65
     donde
    0.64
     allí
    0.63
     όπου
    0.62
    where
    0.61
    Where
    0.60
     où
    0.60
     للاسماء
    0.60
    Act Density 0.080%

    No Known Activations