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

    Neuronpedia

    INDEX
    Explanations

    environments and systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vì
    -0.08
    Terminal
    -0.07
    _Group
    -0.06
     usuarios
    -0.06
     Jetzt
    -0.06
     Belarus
    -0.06
    IB
    -0.06
     ranged
    -0.06
     UserController
    -0.06
    periments
    -0.06
    POSITIVE LOGITS
    .cost
    0.07
    acted
    0.06
    рас
    0.06
    _instructions
    0.06
    ussy
    0.06
     flashback
    0.06
    رك
    0.06
    ][_
    0.06
    -products
    0.06
    IMIZE
    0.06
    Act Density 0.084%

    No Known Activations