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
     Rename
    -0.07
     almış
    -0.06
     duro
    -0.06
    event
    -0.06
    detail
    -0.06
    AGIC
    -0.06
     tube
    -0.06
    maması
    -0.06
    loub
    -0.06
    mayı
    -0.06
    POSITIVE LOGITS
     đồng
    0.07
     parks
    0.06
    誰
    0.06
    .Head
    0.06
    upload
    0.06
    69
    0.06
     trav
    0.06
    341
    0.06
    μερα
    0.06
    ================================================================================
    0.06
    Act Density 0.018%

    No Known Activations