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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sidebar
    -0.06
     kendi
    -0.06
    ůvod
    -0.06
     produce
    -0.06
    Mis
    -0.06
     sina
    -0.06
     vytvoř
    -0.06
    imos
    -0.06
     Texas
    -0.06
    eries
    -0.06
    POSITIVE LOGITS
    )d
    0.07
    UNIT
    0.07
    ¯¯¯¯
    0.07
     (;;)
    0.07
    √
    0.07
    _sd
    0.07
     ratified
    0.06
    �
    0.06
    _disabled
    0.06
    }")
    0.06
    Act Density 0.025%

    No Known Activations