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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formal logic terminology

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

    Mathematical or logical formulas

    np_acts-logits-general · gemini-2.0-flash

    logical formulas and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.65
    atguigu
    -0.57
    Péri
    -0.57
    SBATCH
    -0.54
     مرئيه
    -0.53
    AnchorStyles
    -0.53
    InjectAttribute
    -0.53
    devamını
    -0.52
    BeginInit
    -0.50
    }))
    -0.50
    POSITIVE LOGITS
     formulas
    0.70
     formula
    0.66
     truth
    0.60
     proposition
    0.60
     formules
    0.59
     formulae
    0.57
    Gent
    0.57
     Ground
    0.56
     formule
    0.56
     grounding
    0.55
    Act Density 0.695%

    No Known Activations