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

    Neuronpedia

    INDEX
    Explanations

    Question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     converting
    -0.06
    �
    -0.06
    _salt
    -0.06
     Transit
    -0.06
    项目
    -0.06
    Ｏ
    -0.06
    廳
    -0.06
    離
    -0.06
     svých
    -0.06
    POSITIVE LOGITS
    _wait
    0.07
     tel
    0.07
    _bs
    0.07
     poměr
    0.07
    _first
    0.07
    rc
    0.07
     došlo
    0.07
    .ticket
    0.07
    /Data
    0.06
     wrappers
    0.06
    Act Density 0.018%

    No Known Activations