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

    Neuronpedia

    INDEX
    Explanations

    extracting information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shelley
    -0.07
     bad
    -0.07
    ?q
    -0.07
    oty
    -0.06
    امل
    -0.06
    ाट
    -0.06
    ML
    -0.06
    .Channel
    -0.06
    ีเอ
    -0.06
     Fi
    -0.06
    POSITIVE LOGITS
     anon
    0.07
     complied
    0.06
     imposs
    0.06
     começ
    0.06
     (){↵
    0.06
     hiển
    0.06
    ση
    0.06
    Teacher
    0.06
    _REGION
    0.06
    .virtual
    0.06
    Act Density 0.075%

    No Known Activations