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

    Neuronpedia

    INDEX
    Explanations

    punctuation in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     四
    -0.06
     region
    -0.06
    adients
    -0.06
    ancellation
    -0.06
    noopener
    -0.06
     gradient
    -0.06
     دور
    -0.06
     Jennifer
    -0.06
    agn
    -0.06
     OH
    -0.06
    POSITIVE LOGITS
    .links
    0.07
    之
    0.07
    _ta
    0.07
    estar
    0.06
     blessed
    0.06
    _OW
    0.06
    rored
    0.06
     امید
    0.06
    就是
    0.06
    _Vert
    0.06
    Act Density 0.070%

    No Known Activations