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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '"';↵
    -0.06
    映
    -0.06
    (IT
    -0.06
     ));
↵
    -0.06
    frag
    -0.06
    なの
    -0.06
     phi
    -0.06
    .DAO
    -0.06
    cont
    -0.06
    .LogError
    -0.06
    POSITIVE LOGITS
     buyer
    0.07
    Avoid
    0.06
     holland
    0.06
     misguided
    0.06
     determined
    0.06
    _Con
    0.06
     ejemplo
    0.06
     Ree
    0.06
     Offensive
    0.06
     unused
    0.06
    Act Density 0.417%

    No Known Activations