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

    Neuronpedia

    INDEX
    Explanations

    experimental

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the word “experimental.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     jaké
    -0.07
    "),
↵
    -0.07
     Advisor
    -0.07
    exao
    -0.06
     protects
    -0.06
    .uni
    -0.06
     však
    -0.06
     depicts
    -0.06
     chest
    -0.06
    stdint
    -0.06
    POSITIVE LOGITS
     experimental
    0.08
    �
    0.07
    │
    0.07
    real
    0.07
     Experimental
    0.07
    ocumented
    0.07
    �
    0.07
    DRAW
    0.07
     deliveries
    0.06
    Ư�
    0.06
    Act Density 0.005%

    No Known Activations