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

    Neuronpedia

    INDEX
    Explanations

    orphic (anamorphic)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sitesi
    -0.07
     batz
    -0.07
     kroz
    -0.07
    en
    -0.07
     uphold
    -0.07
    Gaz
    -0.07
    -0.07
     uptime
    -0.07
     Lond
    -0.07
     oración
    -0.07
    POSITIVE LOGITS
     क्षमता
    0.08
     capacités
    0.08
     Capability
    0.08
     surprises
    0.08
    pção
    0.08
    кла
    0.08
     capability
    0.08
     Cros
    0.07
    _RESERVED
    0.07
    нь
    0.07
    Act Density 0.001%
    No Known Activations