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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the token "Re" (as in the start of “Revised”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ct
    -0.08
     theaters
    -0.07
    ceries
    -0.07
    _Game
    -0.06
     consultations
    -0.06
     originating
    -0.06
     arrogant
    -0.06
     grilled
    -0.06
     lecturer
    -0.06
     funding
    -0.06
    POSITIVE LOGITS
    해보
    0.07
    .addRow
    0.06
    theon
    0.06
     workload
    0.06
    @endsection
    0.06
     getField
    0.06
     حقوق
    0.06
     fallback
    0.06
     FIFA
    0.06
    やす
    0.06
    Act Density 0.033%

    No Known Activations