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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     userInfo
    -0.07
    诺
    -0.06
    Thought
    -0.06
    .jpa
    -0.06
    035
    -0.06
     Attention
    -0.06
    存档
    -0.06
     Kush
    -0.06
     शहर
    -0.06
    urahan
    -0.06
    POSITIVE LOGITS
    petto
    0.06
     depois
    0.06
     aquel
    0.06
     draped
    0.06
    第
    0.06
    지막
    0.06
     création
    0.06
     traf
    0.06
    픈
    0.06
    /f
    0.06
    Act Density 0.010%

    No Known Activations