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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canal
    -0.07
     рук
    -0.06
     Cro
    -0.06
     Nob
    -0.06
    ं
    -0.06
    ичних
    -0.06
     Par
    -0.06
    님의
    -0.06
     LAS
    -0.06
    fontName
    -0.06
    POSITIVE LOGITS
    ());↵↵↵
    0.09
    903
    0.06
    ');
↵
    0.06
    ?,?,?,?,
    0.06
    ,'\
    0.06
     ):↵↵
    0.06
    tokens
    0.06
     klein
    0.06
    emsp
    0.06
    ()>↵
    0.06
    Act Density 0.005%

    No Known Activations