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

    Neuronpedia

    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Corner
    -0.07
    �
    -0.06
    Logic
    -0.06
    ONO
    -0.06
    爵
    -0.06
    ěli
    -0.06
    TXT
    -0.06
    ethoven
    -0.06
    	pool
    -0.06
    ального
    -0.06
    POSITIVE LOGITS
     сет
    0.07
    %!
    0.06
    □
    0.06
     mesaj
    0.06
    ออกแบบ
    0.06
    _shortcode
    0.06
    (info
    0.06
    .getTime
    0.06
     tubes
    0.06
     hu
    0.06
    Act Density 0.043%

    No Known Activations