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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    architecture
    -0.07
    ChildScrollView
    -0.07
    ..\
    -0.06
    ansas
    -0.06
     فبراير
    -0.06
    builtin
    -0.06
    Ob
    -0.06
    many
    -0.06
    監督
    -0.06
    ManagedObjectContext
    -0.06
    POSITIVE LOGITS
    Copyright
    0.07
    tae
    0.06
    -static
    0.06
    no
    0.06
     наг
    0.06
    days
    0.06
     pressed
    0.06
     aes
    0.06
    547
    0.06
     routinely
    0.06
    Act Density 0.000%

    No Known Activations