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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recognizing
    -0.08
    学习
    -0.07
    EX
    -0.07
    Required
    -0.07
    _LEN
    -0.07
    מ
    -0.06
     EDM
    -0.06
    ゆ
    -0.06
     ((!
    -0.06
     lest
    -0.06
    POSITIVE LOGITS
     облас
    0.06
    .hstack
    0.06
    /opt
    0.06
     Virt
    0.06
    andscape
    0.06
     ‏
    0.06
     dining
    0.06
    ]/
    0.06
     clan
    0.06
     Öğren
    0.06
    Act Density 0.069%

    No Known Activations