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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KeyName
    -0.07
    لية
    -0.06
    Thunk
    -0.06
     atas
    -0.06
    地區
    -0.06
     कई
    -0.06
    Translate
    -0.06
    _ste
    -0.06
     iyi
    -0.06
     Width
    -0.06
    POSITIVE LOGITS
     glm
    0.07
     "),↵
    0.06
     recycled
    0.06
     whitespace
    0.06
    _tf
    0.06
     conceived
    0.06
     political
    0.06
     fertilizer
    0.06
    A
    0.06
    а
    0.06
    Act Density 0.043%

    No Known Activations