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

    Neuronpedia

    INDEX
    Explanations

    code and logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manžel
    -0.08
     barn
    -0.07
     cavalry
    -0.07
     location
    -0.07
     admin
    -0.06
     dấu
    -0.06
    -rounded
    -0.06
    �
    -0.06
     autofocus
    -0.06
     شکن
    -0.06
    POSITIVE LOGITS
    ぶ
    0.06
    _substr
    0.06
    ा↵↵
    0.06
    EFF
    0.06
    .asm
    0.06
    ूज
    0.06
    ='"
    0.06
     国
    0.06
     estable
    0.06
    ότε
    0.06
    Act Density 0.012%

    No Known Activations