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

    Neuronpedia

    INDEX
    Explanations

    AI Chatbot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estrict
    0.80
     просты
    0.80
    BTW
    0.79
     contacter
    0.76
     boiled
    0.76
    contact
    0.73
     shower
    0.72
    argmin
    0.72
    ixon
    0.72
    🤗
    0.71
    POSITIVE LOGITS
    覧
    0.86
    ความ
    0.82
    מים
    0.76
    ců
    0.75
    etis
    0.73
    licken
    0.72
    ting
    0.72
     Studie
    0.71
    调研
    0.71
    iotics
    0.71
    Act Density 0.003%

    No Known Activations