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

    Neuronpedia

    INDEX
    Explanations

    designed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STANDARD
    -0.07
    це
    -0.07
    ชอบ
    -0.07
     Months
    -0.06
    paste
    -0.06
     */}↵
    -0.06
     proclaimed
    -0.06
    ические
    -0.06
     plight
    -0.06
     경기
    -0.06
    POSITIVE LOGITS
    pin
    0.07
    (sender
    0.07
     gmail
    0.06
    Encryption
    0.06
     Ups
    0.06
    ﾍ
    0.06
    _COMPLETE
    0.06
     fotoğraf
    0.06
     Bond
    0.06
    .Generated
    0.06
    Act Density 0.000%

    No Known Activations