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

    Neuronpedia

    INDEX
    Explanations

    Circuit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joan
    -0.08
    nç
    -0.08
    _cmos
    -0.08
    ubyte
    -0.07
     saya
    -0.07
    (the
    -0.07
    --}}↵
    -0.07
    _Vector
    -0.06
     bv
    -0.06
     vain
    -0.06
    POSITIVE LOGITS
     intersection
    0.07
    需求
    0.07
    ข
    0.07
    Թ
    0.07
    地上
    0.07
    -to
    0.07
    粥
    0.06
    ialized
    0.06
    reads
    0.06
     Searching
    0.06
    Act Density 0.001%

    No Known Activations