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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLIENT
    -0.07
     депут
    -0.06
    edla
    -0.06
     SEAL
    -0.06
    학과
    -0.06
    .Col
    -0.06
    人の
    -0.06
     mag
    -0.06
    README
    -0.06
     taped
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    \"",↵
    0.06
    �
    0.06
    ы
    0.06
    USTER
    0.06
     "<?
    0.06
    atürk
    0.06
    ку
    0.06
     육
    0.06
     breathable
    0.06
    Act Density 0.055%

    No Known Activations