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

    Neuronpedia

    INDEX
    Explanations

    Chinese places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (super
    -0.07
     fluids
    -0.06
     Marino
    -0.06
    石
    -0.06
     premiums
    -0.06
     thr
    -0.06
     quotations
    -0.06
    _rectangle
    -0.06
    868
    -0.06
    lar
    -0.06
    POSITIVE LOGITS
    उ
    0.06
     delays
    0.06
     jin
    0.06
     ermög
    0.06
     Kill
    0.06
    �
    0.06
     breeze
    0.06
    ايي
    0.06
    atched
    0.06
     ever
    0.06
    Act Density 0.016%

    No Known Activations