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

    Neuronpedia

    INDEX
    Explanations

    expressions of exasperation or sarcasm

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

    Follows opinion or commentary words

    np_acts-logits-general · gemini-2.0-flash

    unimportant or silly things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tajam
    -0.35
     silueta
    -0.30
     badan
    -0.30
     rocas
    -0.29
     vécu
    -0.28
     noches
    -0.28
     dipa
    -0.28
     cuerdas
    -0.28
     trusted
    -0.27
     exposing
    -0.27
    POSITIVE LOGITS
    astéroïdes
    0.69
    contentLoaded
    0.66
    MemoryWarning
    0.65
    ⟬
    0.58
     يتيمه
    0.58
    webElementGuid
    0.56
     createSlice
    0.56
    RenderAtEndOf
    0.56
     silly
    0.55
    expandindo
    0.54
    Act Density 0.409%

    No Known Activations