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

    Neuronpedia

    INDEX
    Explanations

    concepts related to choices and consequences in decision-making scenarios

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

    Follows common words or short phrases

    np_acts-logits-general · gemini-2.0-flash

    legal, financial, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.63
    MemoryWarning
    -0.61
    таратура
    -0.55
    MessageOf
    -0.55
    IBOutlet
    -0.55
     disambiguazione
    -0.54
    ########.
    -0.54
     vocês
    -0.52
    UnsafeEnabled
    -0.52
     Exactos
    -0.52
    POSITIVE LOGITS
     sile
    0.36
     fú
    0.35
     dro
    0.35
     pl
    0.33
     fide
    0.33
     stör
    0.33
     YouTube
    0.33
     PL
    0.32
     fur
    0.32
    strtolower
    0.32
    Act Density 0.615%

    No Known Activations