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

    Neuronpedia

    INDEX
    Explanations

    [:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ecuador
    -0.07
     dr
    -0.07
     saint
    -0.06
     incorpor
    -0.06
     resurgence
    -0.06
    .offsetWidth
    -0.06
     Marcos
    -0.06
     tty
    -0.06
     uses
    -0.06
     reveals
    -0.06
    POSITIVE LOGITS
    (audio
    0.07
    Modifiers
    0.07
    产生
    0.06
    ){
    0.06
    ()){
↵
    0.06
    979
    0.06
    騎
    0.06
    formerly
    0.06
    "${
    0.06
     bağ
    0.06
    Act Density 0.005%

    No Known Activations