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

    Neuronpedia

    INDEX
    Explanations

    Blog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrow
    -0.06
     Mongo
    -0.06
     gameOver
    -0.06
    .savefig
    -0.06
     tarea
    -0.06
    recated
    -0.06
    优秀
    -0.06
    perial
    -0.06
    ’B
    -0.06
    "<
    -0.06
    POSITIVE LOGITS
    评
    0.07
     spoke
    0.07
     demanding
    0.07
     함
    0.07
    �
    0.06
    =false
    0.06
    �
    0.06
     اش
    0.06
     immoral
    0.06
     Storage
    0.06
    Act Density 0.001%

    No Known Activations