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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _entity
    -0.07
    445
    -0.07
    315
    -0.07
     남
    -0.06
     advantageous
    -0.06
     Чем
    -0.06
    紹
    -0.06
    _mu
    -0.06
     transporter
    -0.06
    -0.06
    POSITIVE LOGITS
    aterno
    0.07
    setVisible
    0.06
    ुध
    0.06
    price
    0.06
     난
    0.06
    �
    0.06
     Inc
    0.06
     سیاسی
    0.06
     Sweet
    0.06
    �
    0.06
    Act Density 0.105%

    No Known Activations