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

    Neuronpedia

    INDEX
    Explanations

    facebook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Servers
    -0.08
     разв
    -0.08
     assortment
    -0.07
    пов
    -0.07
    outines
    -0.07
    ைந்த
    -0.07
     mundane
    -0.07
     modules
    -0.07
     ক
    -0.07
     berkembang
    -0.07
    POSITIVE LOGITS
    =torch
    0.10
     Commissie
    0.09
    (torch
    0.09
     pretrained
    0.09
     Universitat
    0.09
    _APPRO
    0.09
     deelname
    0.08
    geschlossen
    0.08
     uppsk
    0.08
     pesquisadores
    0.08
    Act Density 0.002%

    No Known Activations