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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ski
    -0.07
     amps
    -0.07
     letters
    -0.07
     interval
    -0.07
    istring
    -0.07
    -ft
    -0.07
     rise
    -0.07
     discret
    -0.07
     suggests
    -0.07
    below
    -0.07
    POSITIVE LOGITS
     धर
    0.06
    توبر
    0.06
     Emmanuel
    0.06
    ，更
    0.06
     انر
    0.06
     Award
    0.06
     всі
    0.06
    ś
    0.06
     governed
    0.06
     lineNumber
    0.06
    Act Density 0.075%

    No Known Activations