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

    Neuronpedia

    INDEX
    Explanations

    labeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     العق
    -0.07
     fg
    -0.06
     seçenek
    -0.06
     Diy
    -0.06
     heel
    -0.06
     मजब
    -0.06
     trout
    -0.06
    Gem
    -0.06
    quisite
    -0.06
    eat
    -0.06
    POSITIVE LOGITS
     called
    0.08
    called
    0.07
     termed
    0.07
     наз
    0.07
     sprung
    0.07
    ]",
    0.07
    888
    0.07
    delta
    0.07
    =count
    0.06
    gregator
    0.06
    Act Density 0.106%

    No Known Activations