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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     medidas
    -0.07
     abandonment
    -0.06
     Hung
    -0.06
     hoops
    -0.06
     indeed
    -0.06
     chơi
    -0.06
    으니
    -0.06
    ้อ
    -0.06
     goed
    -0.06
    POSITIVE LOGITS
    (stderr
    0.07
    ,$
    0.06
     Vietnamese
    0.06
     Calvin
    0.06
    읍
    0.06
    untu
    0.06
     discord
    0.06
    laş
    0.06
    _formatted
    0.06
    ////////
    0.06
    Act Density 0.010%

    No Known Activations