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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twist
    -0.07
    角色
    -0.07
     mirror
    -0.07
    Europe
    -0.06
     ребенок
    -0.06
     Replace
    -0.06
     конца
    -0.06
    _out
    -0.06
     riches
    -0.06
    .cons
    -0.06
    POSITIVE LOGITS
     Rath
    0.06
    弥
    0.06
    )initWithFrame
    0.06
     HCI
    0.06
     पड
    0.06
     DN
    0.06
     &#
    0.06
     GRE
    0.06
    راد
    0.06
     DataContext
    0.05
    Act Density 0.024%

    No Known Activations