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

    Neuronpedia

    INDEX
    Explanations

    punctuations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clinton
    -0.07
     liebe
    -0.06
     streets
    -0.06
     Patton
    -0.06
     Coral
    -0.06
     ذکر
    -0.06
     linen
    -0.06
    .Vertical
    -0.06
    .art
    -0.06
    오는
    -0.06
    POSITIVE LOGITS
    ertificate
    0.07
     knife
    0.07
     additives
    0.07
     sealed
    0.07
    PLEASE
    0.06
     Installer
    0.06
    _RECE
    0.06
     Supplementary
    0.06
     destined
    0.06
     compressed
    0.06
    Act Density 0.001%

    No Known Activations