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

    Neuronpedia

    INDEX
    Explanations

    references to discussions about personal experiences and insights

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

    talking about interviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobal
    -0.67
     noDo
    -0.64
     oprot
    -0.61
     Италијани
    -0.61
     newOwner
    -0.60
    CloseOperation
    -0.60
    ValueGeneration
    -0.59
    onOptions
    -0.59
     ExecuteAsync
    -0.59
     ModelRenderer
    -0.58
    POSITIVE LOGITS
     interview
    0.45
     adelant
    0.39
    entretien
    0.39
     интервью
    0.38
     interviewed
    0.37
     entrevistas
    0.37
    tiéndose
    0.36
     entrevist
    0.36
     raça
    0.35
     hablamos
    0.35
    Act Density 0.018%

    No Known Activations