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

    Neuronpedia

    INDEX
    Explanations

    informal phrases and expressions of agreement or politeness

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

    conversational words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ErrIntOverflow
    -0.43
     conclusão
    -0.42
    แห่ง
    -0.38
     Physiol
    -0.38
    organisation
    -0.37
     lục
    -0.37
     organisation
    -0.37
    yelidikan
    -0.37
    SBATCH
    -0.36
    aksikan
    -0.36
    POSITIVE LOGITS
    ftagPool
    0.50
     esterni
    0.46
     nonatomic
    0.45
    లాలు
    0.44
     שוליים
    0.44
     HasFactory
    0.44
     חיצוניים
    0.43
     kasarigan
    0.43
    ValueStyle
    0.42
    EnableWeb
    0.42
    Act Density 0.044%

    No Known Activations