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

    Neuronpedia

    INDEX
    Explanations

    otes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curse
    -0.07
    Wave
    -0.06
     bleiben
    -0.06
    脸
    -0.06
     qualified
    -0.06
    ΑΔ
    -0.06
     intéress
    -0.06
     کری
    -0.06
    Markdown
    -0.06
    consider
    -0.06
    POSITIVE LOGITS
     boots
    0.07
     Academic
    0.07
     bundle
    0.07
    _form
    0.06
    ERT
    0.06
    (assign
    0.06
    енности
    0.06
    Beginning
    0.06
     planta
    0.06
     bird
    0.06
    Act Density 0.000%

    No Known Activations