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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contractors
    -0.07
    dělení
    -0.07
     สาข
    -0.07
    .FETCH
    -0.07
     Zoo
    -0.06
    nímu
    -0.06
     요청
    -0.06
     THAN
    -0.06
     inspectors
    -0.06
     फल
    -0.06
    POSITIVE LOGITS
     rio
    0.06
    lice
    0.06
    ệ
    0.06
    \Module
    0.06
    Matrix
    0.06
    Esc
    0.06
    ewood
    0.05
    囲
    0.05
     CString
    0.05
     accelerate
    0.05
    Act Density 0.017%

    No Known Activations