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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рож
    -0.07
    otel
    -0.07
    Neg
    -0.07
     files
    -0.06
    nod
    -0.06
    гов
    -0.06
    िर
    -0.06
    Menu
    -0.06
    ्रह
    -0.06
    菌
    -0.06
    POSITIVE LOGITS
     generado
    0.07
     Propel
    0.07
     Spear
    0.06
     overhe
    0.06
    fluence
    0.06
     $#
    0.06
     ActiveForm
    0.06
     Exceptions
    0.06
     JSX
    0.06
    	cf
    0.06
    Act Density 0.005%

    No Known Activations