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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     virtues
    -0.07
     philosophers
    -0.07
    objects
    -0.06
    icable
    -0.06
     반
    -0.06
    Rows
    -0.06
     cũ
    -0.06
     oppressed
    -0.06
    GitHub
    -0.06
     더욱
    -0.06
    POSITIVE LOGITS
    (nome
    0.07
    _minimum
    0.07
    .bounds
    0.07
    んだ
    0.07
    (close
    0.07
     накоп
    0.07
    eyle
    0.06
     invaders
    0.06
    Indices
    0.06
    INavigation
    0.06
    Act Density 0.122%

    No Known Activations