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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аних
    -0.07
    مد
    -0.07
     operational
    -0.07
    олько
    -0.07
    PostalCodesNL
    -0.07
    προ
    -0.07
    浦
    -0.06
     hm
    -0.06
    ož
    -0.06
    兄
    -0.06
    POSITIVE LOGITS
    _NR
    0.06
     Appears
    0.06
    .L
    0.06
    .
↵
    0.06
    including
    0.06
    =-
    0.06
     };↵
    0.06
    -metadata
    0.06
    258
    0.06
    ."'
    0.06
    Act Density 0.012%

    No Known Activations