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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zejména
    -0.08
    Blank
    -0.07
     prova
    -0.07
     revolutions
    -0.06
     hồi
    -0.06
     Hunts
    -0.06
    ections
    -0.06
    脚
    -0.06
     sond
    -0.06
    iydi
    -0.06
    POSITIVE LOGITS
    动生成
    0.07
     Village
    0.07
     Essence
    0.07
    Already
    0.07
    .Dict
    0.06
    .city
    0.06
     แหล
    0.06
    -winning
    0.06
    closest
    0.06
     ANSW
    0.06
    Act Density 0.002%

    No Known Activations