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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тро
    -0.07
     tab
    -0.06
    _WE
    -0.06
     terr
    -0.06
    Wnd
    -0.06
     стр
    -0.06
     то
    -0.06
     AppCompatActivity
    -0.06
    خراج
    -0.06
     phép
    -0.06
    POSITIVE LOGITS
    .Offset
    0.07
     Golf
    0.06
    estination
    0.06
    iance
    0.06
    	expect
    0.06
     Nicholas
    0.06
     Release
    0.06
    airo
    0.06
     유지
    0.06
     bible
    0.06
    Act Density 0.009%

    No Known Activations