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

    Neuronpedia

    INDEX
    Explanations

    ology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственного
    -0.06
    legate
    -0.06
    _route
    -0.06
    (char
    -0.06
    strained
    -0.06
     reduces
    -0.06
     Rewrite
    -0.06
    Relations
    -0.06
    -election
    -0.06
    _KEEP
    -0.06
    POSITIVE LOGITS
    країн
    0.06
     Parr
    0.06
     Sor
    0.06
     cond
    0.06
     recruit
    0.06
     Further
    0.06
    итися
    0.06
    СТ
    0.06
    �
    0.06
    oblin
    0.06
    Act Density 0.013%

    No Known Activations