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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal and lifestyle choices

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

    descriptive attributes and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cena
    -0.36
     Segovia
    -0.36
    volved
    -0.35
     involved
    -0.35
    OPSIS
    -0.35
    Spotted
    -0.35
    sentinel
    -0.35
    gregation
    -0.35
     Knudsen
    -0.34
     spotted
    -0.34
    POSITIVE LOGITS
    StoryboardSegue
    0.71
     autorytatywna
    0.65
    expandindo
    0.63
    Legături
    0.58
     مشين
    0.56
    ModelSerializer
    0.54
    TagMode
    0.52
    BeginContext
    0.52
     doInBackground
    0.51
    ViewImports
    0.49
    Act Density 0.007%

    No Known Activations