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
    _ST
    -0.08
     по
    -0.07
    _foot
    -0.07
     mingle
    -0.06
    TREE
    -0.06
     прям
    -0.06
    _join
    -0.06
     adapt
    -0.06
    Weight
    -0.06
    Ball
    -0.06
    POSITIVE LOGITS
    catid
    0.07
    .toJSON
    0.06
     Gutenberg
    0.06
    .JComboBox
    0.06
     усл
    0.06
     chvíli
    0.06
     komment
    0.06
     фундамент
    0.06
     Kil
    0.06
     predecess
    0.06
    Act Density 0.002%

    No Known Activations