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

    Neuronpedia

    INDEX
    Explanations

    July

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     див
    -0.07
     recharge
    -0.07
    Photos
    -0.06
     κον
    -0.06
     pel
    -0.06
     authorised
    -0.06
    Edge
    -0.06
     Brew
    -0.06
    í
    -0.06
     مدر
    -0.06
    POSITIVE LOGITS
    enderror
    0.07
    (";
    0.07
    왔다
    0.07
    ubah
    0.06
    -your
    0.06
    山市
    0.06
    udson
    0.06
     Budget
    0.06
    мер
    0.06
    .',
    0.06
    Act Density 0.007%

    No Known Activations