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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _instruction
    -0.06
    _Render
    -0.06
     Durham
    -0.06
     versa
    -0.06
     cheat
    -0.06
    138
    -0.06
    ;text
    -0.06
     balls
    -0.06
     extent
    -0.06
     titular
    -0.06
    POSITIVE LOGITS
    μία
    0.06
     الصن
    0.06
    ュ
    0.06
    (hr
    0.06
    otomy
    0.06
    咲
    0.06
    еления
    0.06
     meget
    0.06
    لیت
    0.06
    (tree
    0.06
    Act Density 0.003%

    No Known Activations