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

    Neuronpedia

    INDEX
    Explanations

    instances of completely empty or termination tokens

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

    purchasing links devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jefes
    -0.43
     griega
    -0.43
     burbujas
    -0.43
     Comunicação
    -0.40
     idéia
    -0.39
     corrientes
    -0.39
     calorías
    -0.39
     incluida
    -0.38
     belang
    -0.37
     voetballer
    -0.37
    POSITIVE LOGITS
    ंदीखरीदारी
    0.88
     CanadaChoose
    0.68
    StructEnd
    0.67
    IUrlHelper
    0.65
     APL
    0.64
    InjectAttribute
    0.63
    UnusedPrivate
    0.63
     COT
    0.62
    ➟
    0.61
    edoc
    0.59
    Act Density 0.053%

    No Known Activations