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

    Neuronpedia

    INDEX
    Explanations

    Sheriff

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on occurrences of the word “Sheriff.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nodes
    -0.07
    +A
    -0.07
     Great
    -0.07
     Nicola
    -0.07
     Intelligent
    -0.07
     nodes
    -0.06
    Elite
    -0.06
    plug
    -0.06
     simples
    -0.06
     zeal
    -0.06
    POSITIVE LOGITS
     sheriff
    0.12
     Sheriff
    0.11
     sher
    0.08
     rhs
    0.07
    рис
    0.07
     guardian
    0.07
     if
    0.07
    lf
    0.07
    svp
    0.06
    193
    0.06
    Act Density 0.002%

    No Known Activations