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

    Neuronpedia

    INDEX
    Explanations

    relevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ัตน
    -0.07
    ilerin
    -0.06
     signin
    -0.06
    userinfo
    -0.06
    랜드
    -0.06
    ��
    -0.06
     contents
    -0.06
    КТ
    -0.06
    _nan
    -0.06
     бо
    -0.06
    POSITIVE LOGITS
    ，小
    0.07
     раствор
    0.07
    atee
    0.06
     got
    0.06
     relevant
    0.06
     Viet
    0.06
     così
    0.06
     every
    0.06
    िह
    0.06
    lexer
    0.06
    Act Density 0.001%

    No Known Activations