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

    Neuronpedia

    INDEX
    Explanations

    Prefixes of technical terms and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arises
    0.27
     is
    0.25
     ανθρώ
    0.23
     в
    0.23
     raio
    0.23
     घेणे
    0.22
    umbled
    0.22
     serem
    0.22
     Belgi
    0.22
    riy
    0.22
    POSITIVE LOGITS
    6
    0.27
    Contents
    0.23
    5
    0.23
    サポート
    0.22
    fitrión
    0.22
    8
    0.22
    7
    0.22
    islav
    0.22
    más
    0.21
    ივ
    0.21
    Act Density 0.101%

    No Known Activations