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

    Neuronpedia

    INDEX
    Explanations

    56

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pickup
    -0.07
    cio
    -0.07
    /@
    -0.07
    _rectangle
    -0.06
    ักงาน
    -0.06
     Zusammen
    -0.06
    :</
    -0.06
     정부
    -0.06
    äre
    -0.06
     maxx
    -0.06
    POSITIVE LOGITS
     classmates
    0.07
     SAX
    0.06
     �
    0.06
    .sal
    0.06
    富
    0.06
    andard
    0.06
     söz
    0.06
    �
    0.06
    employment
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations