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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أر
    -0.08
    (chr
    -0.07
     fittings
    -0.07
     дней
    -0.06
     chế
    -0.06
     Jiang
    -0.06
     її
    -0.06
     Jessie
    -0.06
    CU
    -0.06
     moz
    -0.06
    POSITIVE LOGITS
     compressed
    0.07
    .goal
    0.06
     пис
    0.06
     przez
    0.06
    _m
    0.06
    $username
    0.06
     array
    0.06
     الجم
    0.06
    'nda
    0.06
     드립니다
    0.06
    Act Density 0.205%

    No Known Activations