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

    Neuronpedia

    INDEX
    Explanations

    references to generic programming concepts and interfaces

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

    must satisfies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.49
     يتيمه
    -0.44
    featureID
    -0.43
    +:+
    -0.41
    Meto
    -0.41
    TypedDataSet
    -0.40
     الحره
    -0.40
     tournage
    -0.39
    felizmente
    -0.39
    UserScript
    -0.38
    POSITIVE LOGITS
    MERCE
    0.43
     perceptual
    0.43
    pantalones
    0.41
    ophilic
    0.41
    deri
    0.41
     reban
    0.40
     construed
    0.40
     znal
    0.40
     alıntı
    0.40
     calendriers
    0.40
    Act Density 0.187%

    No Known Activations