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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    Stretch
    -0.07
    cool
    -0.07
    _AGENT
    -0.06
    Trees
    -0.06
     crude
    -0.06
     timeless
    -0.06
    ологія
    -0.06
    َه
    -0.06
    Reading
    -0.06
    POSITIVE LOGITS
     Abd
    0.06
     responded
    0.06
     vig
    0.06
     claiming
    0.06
     ارتفاع
    0.06
     decorate
    0.06
     persisted
    0.06
     inbox
    0.06
     Vir
    0.06
     unhealthy
    0.06
    Act Density 0.007%

    No Known Activations