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

    Neuronpedia

    INDEX
    Explanations

    bookshelf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capturing
    -0.08
    appers
    -0.08
     handling
    -0.08
     snelheid
    -0.07
     interf
    -0.07
     portrayal
    -0.07
     알려
    -0.07
    Yo
    -0.07
     Qo
    -0.07
     Yo
    -0.07
    POSITIVE LOGITS
    helves
    0.11
     уют
    0.10
     ძ
    0.10
     eclectic
    0.10
     წევ
    0.10
    dale
    0.09
    гоҳи
    0.09
     bookshelf
    0.09
     პარლამენტ
    0.09
     бәт
    0.09
    Act Density 0.003%

    No Known Activations