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

    Neuronpedia

    INDEX
    Explanations

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    בסופו
    -0.08
     milf
    -0.07
    transport
    -0.07
    蒗
    -0.07
    di
    -0.07
    既有
    -0.07
    都没
    -0.07
    ond
    -0.07
    NavigatorMove
    -0.07
     wissen
    -0.06
    POSITIVE LOGITS
     MATERIAL
    0.07
     sergeant
    0.07
     ISO
    0.07
     Bros
    0.07
    塞尔
    0.07
    TOOLS
    0.07
     Weber
    0.07
     Nights
    0.07
     HIT
    0.07
    出国
    0.06
    Act Density 0.002%

    No Known Activations