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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Xi
    -0.08
    Sparse
    -0.07
     Duis
    -0.07
    微观
    -0.07
     data
    -0.07
    Drv
    -0.07
    scene
    -0.06
     Unsigned
    -0.06
     combust
    -0.06
     national
    -0.06
    POSITIVE LOGITS
     GM
    0.08
     latin
    0.07
    と言われ
    0.07
    绋
    0.07
    ⊋
    0.06
    _MODEL
    0.06
    _ste
    0.06
    文化底蕴
    0.06
    ś
    0.06
     competency
    0.06
    Act Density 0.114%

    No Known Activations