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

    Neuronpedia

    INDEX
    Explanations

    Requests/Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -track
    -0.07
    αρίου
    -0.06
     Werk
    -0.06
    рид
    -0.06
     sts
    -0.06
     участи
    -0.06
     tapes
    -0.06
     coupling
    -0.06
     bilder
    -0.06
    Dialogue
    -0.06
    POSITIVE LOGITS
    鼻
    0.07
    caling
    0.07
    invoices
    0.07
    講
    0.06
    distinct
    0.06
    social
    0.06
     veget
    0.06
     startTime
    0.06
    ←
    0.06
    сит
    0.06
    Act Density 0.167%

    No Known Activations