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

    Neuronpedia

    INDEX
    Explanations

    software learning environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     typography
    -0.09
     parentheses
    -0.08
     punctuation
    -0.08
    ناصر
    -0.08
     забот
    -0.08
    امين
    -0.08
    .Padding
    -0.08
     collectiv
    -0.08
    شهد
    -0.08
    Horizontal
    -0.07
    POSITIVE LOGITS
     sandbox
    0.13
    sandbox
    0.13
     playground
    0.12
     Sandbox
    0.11
     테스트
    0.11
     demo
    0.11
    _demo
    0.11
    Sandbox
    0.11
    Demo
    0.11
    demo
    0.11
    Act Density 0.022%

    No Known Activations