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

    Neuronpedia

    INDEX
    Explanations

    Facts and suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KEEP
    -0.08
    722
    -0.06
    umbled
    -0.06
    245
    -0.06
    451
    -0.06
     hơn
    -0.06
    _mas
    -0.06
    brain
    -0.06
    Hours
    -0.06
     movements
    -0.06
    POSITIVE LOGITS
     допомогою
    0.08
     })↵↵
    0.07
    لفة
    0.07
    _WEEK
    0.06
     DN
    0.06
     ov
    0.06
     nf
    0.06
    Override
    0.06
    _STS
    0.06
     Zodiac
    0.06
    Act Density 0.042%

    No Known Activations