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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oir
    -0.08
    орош
    -0.07
    �
    -0.06
    mey
    -0.06
    _validator
    -0.06
    عکس
    -0.06
    nk
    -0.06
    packages
    -0.06
    ュ
    -0.06
    Would
    -0.06
    POSITIVE LOGITS
    /script
    0.06
     alters
    0.06
     deception
    0.06
    ;<
    0.06
    ่ำ
    0.06
    ={
    0.06
    |max
    0.06
    iče
    0.06
     Üy
    0.06
     meme
    0.06
    Act Density 0.241%

    No Known Activations