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

    Neuronpedia

    INDEX
    Explanations

    guideline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intersection
    -0.07
    ूसर
    -0.06
     pw
    -0.06
     epochs
    -0.06
     excl
    -0.06
     ttk
    -0.06
     вход
    -0.06
    存在
    -0.06
    .ba
    -0.06
     SID
    -0.06
    POSITIVE LOGITS
     guideline
    0.07
     helpful
    0.07
    walking
    0.07
     blues
    0.07
    ُّ
    0.06
     Formatting
    0.06
    ді
    0.06
    :add
    0.06
    professional
    0.06
     Dit
    0.06
    Act Density 0.000%

    No Known Activations