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

    Neuronpedia

    INDEX
    Explanations

    Chemistry/chemical reactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mock
    -0.09
     DROP
    -0.07
    Construct
    -0.07
     DataLoader
    -0.07
     democracy
    -0.07
     dök
    -0.07
     milling
    -0.07
    ρέπει
    -0.07
     corridors
    -0.07
    ="
    -0.06
    POSITIVE LOGITS
     incoming
    0.06
     Constantin
    0.06
    出版
    0.06
    CppObject
    0.06
     daytime
    0.06
    nya
    0.06
    172
    0.06
    _not
    0.06
    _imag
    0.06
    atory
    0.06
    Act Density 0.027%

    No Known Activations