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

    Neuronpedia

    INDEX
    Explanations

    choreography

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of choreography or choreographic roles (e.g. “choreographer,” “choreographing,” and related dance‐creation terms”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    riends
    -0.07
     reduction
    -0.06
     Samar
    -0.06
     семей
    -0.06
     rewind
    -0.06
     padx
    -0.06
     ödem
    -0.06
    .LAZY
    -0.06
     BITTE
    -0.06
    맥
    -0.06
    POSITIVE LOGITS
     chore
    0.07
     HG
    0.06
     télé
    0.06
     Homework
    0.06
    oub
    0.06
     shallow
    0.06
     chores
    0.06
    _emb
    0.06
     Chore
    0.06
    .zeros
    0.06
    Act Density 0.001%

    No Known Activations