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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical inequalities and specifications

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

    "basic" followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HostException
    -0.52
     exclusives
    -0.47
     exclusively
    -0.46
    SerializeField
    -0.45
    tranno
    -0.44
    
    -0.44
    StylePriority
    -0.43
    himovic
    -0.43
    yargs
    -0.42
     GreatSchools
    -0.42
    POSITIVE LOGITS
     basic
    1.68
    Basic
    1.56
    basic
    1.55
     Basic
    1.54
     básico
    1.38
     básica
    1.32
     básicos
    1.29
     básicas
    1.25
    BASIC
    1.23
     BASIC
    1.20
    Act Density 0.031%

    No Known Activations