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

    Neuronpedia

    INDEX
    Explanations

    options, freedom of choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attraction
    -0.08
     attracted
    -0.08
    inux
    -0.08
     Attraction
    -0.08
     Ellen
    -0.08
     fasc
    -0.07
     podstaw
    -0.07
     ricon
    -0.07
     htt
    -0.07
     attract
    -0.07
    POSITIVE LOGITS
    不限
    0.10
     selbstverständlich
    0.08
     nemus
    0.08
     होइन
    0.08
    េត្ត
    0.08
    লেও
    0.08
     मात्रै
    0.08
    顺
    0.08
    lüğ
    0.08
     უბრალოდ
    0.08
    Act Density 0.029%

    No Known Activations