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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron never fires—it’s essentially dead and does not detect any pattern in the input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ice
    -0.08
    rella
    -0.07
    'll
    -0.07
     fir
    -0.06
    -loading
    -0.06
    datable
    -0.06
    Coder
    -0.06
    }>
    -0.06
    Pa
    -0.06
    LogLevel
    -0.06
    POSITIVE LOGITS
     seule
    0.07
     glVertex
    0.07
    ческие
    0.07
     adultes
    0.06
     это
    0.06
     externally
    0.06
    =max
    0.06
    "url
    0.06
    емых
    0.06
     algae
    0.06
    Act Density 0.005%

    No Known Activations