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

    Neuronpedia

    INDEX
    Explanations

    numerical information, specifically reference to numeric values and their significance in context

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

    The number 0 followed by a number greater than 0

    np_acts-logits-general · gemini-2.0-flash

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.73
    ])):
    -0.64
    }),
    -0.64
     pleaſure
    -0.62
     houſe
    -0.62
     anſ
    -0.61
    osity
    -0.60
     ſta
    -0.60
    __))
    -0.59
     ſtre
    -0.59
    POSITIVE LOGITS
     مشين
    0.70
    İstinadlar
    0.64
     يتيمه
    0.59
    LookAnd
    0.54
    Izvori
    0.54
    
    0.53
    ItemLayout
    0.53
    extAlignment
    0.51
     gynhyrchwyd
    0.51
     resultCode
    0.49
    Act Density 0.146%

    No Known Activations