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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    This neuron never activates (all its activation values are zero), so it doesn’t detect or respond to any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     københavn
    -0.07
    _"+
    -0.06
    "%(
    -0.06
     attack
    -0.06
     Bosnia
    -0.06
    Mes
    -0.06
     themselves
    -0.06
     deniz
    -0.06
     Adidas
    -0.06
    рави
    -0.06
    POSITIVE LOGITS
    advertisement
    0.07
    :checked
    0.06
    tim
    0.06
     takže
    0.06
    .var
    0.06
     superstar
    0.06
     درمان
    0.06
    different
    0.06
    (messages
    0.06
     зда
    0.06
    Act Density 0.009%

    No Known Activations