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

    Neuronpedia

    INDEX
    Explanations

    rates/prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .proc
    -0.07
    離
    -0.07
     colleague
    -0.06
    NBC
    -0.06
    >ID
    -0.06
    @Resource
    -0.06
    文化
    -0.06
     Defender
    -0.06
     DF
    -0.06
    _school
    -0.06
    POSITIVE LOGITS
     пис
    0.07
     fiss
    0.06
     wer
    0.06
     citt
    0.06
    ships
    0.06
    assignments
    0.06
     erste
    0.06
     plaisir
    0.06
    valu
    0.06
    忍
    0.06
    Act Density 0.010%

    No Known Activations