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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .za
    -0.07
    filer
    -0.06
    ана
    -0.06
    ibal
    -0.06
     AssemblyFileVersion
    -0.06
    ��
    -0.06
     Jensen
    -0.06
    ج
    -0.06
    обра�
    -0.06
    NX
    -0.06
    POSITIVE LOGITS
    auth
    0.07
    Ст
    0.06
    quisitions
    0.06
     promotions
    0.06
    技
    0.06
    _CUDA
    0.06
     Mond
    0.06
    _sum
    0.06
    递
    0.06
     �
    0.06
    Act Density 0.029%

    No Known Activations