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

    Neuronpedia

    INDEX
    Explanations

    Ap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sour
    -0.07
    Prec
    -0.07
    ANGER
    -0.07
    DATA
    -0.06
    IDDLE
    -0.06
    metro
    -0.06
    ميم
    -0.06
     одному
    -0.06
    ΕΥ
    -0.06
     ERROR
    -0.06
    POSITIVE LOGITS
     Δε
    0.06
    \Requests
    0.06
     Victorian
    0.06
     Resize
    0.06
                        ↵                    ↵
    0.06
     Parties
    0.06
     Mk
    0.06
     Bs
    0.06
     Might
    0.06
     частина
    0.06
    Act Density 0.075%

    No Known Activations