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

    Neuronpedia

    INDEX
    Explanations

    first world problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erg
    -0.07
     itr
    -0.07
     blow
    -0.06
    сон
    -0.06
     quindi
    -0.06
    pai
    -0.06
    slide
    -0.06
    laus
    -0.06
    CL
    -0.06
    getEmail
    -0.06
    POSITIVE LOGITS
    许多人
    0.07
    表达了
    0.07
     ihrem
    0.06
    海外市场
    0.06
    larını
    0.06
    _sess
    0.06
     uniquely
    0.06
     divert
    0.06
    ��
    0.06
     dimensional
    0.06
    Act Density 0.000%

    No Known Activations