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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and structured formats typically seen in academic or technical writing

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

    aligned equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.64
    ----</
    -0.52
     препратки
    -0.49
    
    -0.46
     незавершена
    -0.46
    ).</
    -0.45
     JpaRepository
    -0.45
    Datuak
    -0.45
    KURZBESCHREIBUNG
    -0.44
    諷
    -0.43
    POSITIVE LOGITS
    ."
    0.43
    ագրություններ
    0.42
    ↵↵↵
    0.42
     defaultstate
    0.41
    ↵↵
    0.40
    ↵↵↵↵
    0.40
    ”
    0.40
    .”
    0.39
    equation
    0.38
     horaires
    0.38
    Act Density 0.106%

    No Known Activations