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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULD
    -0.06
    iah
    -0.06
    rec
    -0.06
    �제
    -0.06
    äs
    -0.06
    vertex
    -0.06
     █
    -0.06
    Rank
    -0.06
    إن
    -0.06
     injunction
    -0.06
    POSITIVE LOGITS
     screwed
    0.07
    /backend
    0.07
     وقت
    0.07
     良
    0.07
    _DA
    0.07
     تجربه
    0.06
     ellipt
    0.06
     😀
    0.06
     �
    0.06
    _opt
    0.06
    Act Density 0.011%

    No Known Activations