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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .outer
    -0.07
     التط
    -0.07
    绽
    -0.07
    surface
    -0.07
     Millionen
    -0.07
    庄严
    -0.07
    MASConstraintMaker
    -0.07
    跷
    -0.06
    (fill
    -0.06
     IU
    -0.06
    POSITIVE LOGITS
     segundo
    0.07
     Clar
    0.07
    _pad
    0.07
    另
    0.07
    �
    0.07
     Principle
    0.07
     Offline
    0.07
     offline
    0.07
     nos
    0.06
    erase
    0.06
    Act Density 0.005%

    No Known Activations