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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    This neuron responds to present-tense verbs ending in “-ing” (gerunds/participles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Weight
    -0.07
    Waiting
    -0.06
     ol
    -0.06
     responsibility
    -0.06
     numberOf
    -0.06
    Si
    -0.06
    ιο
    -0.06
    of
    -0.06
    .dispose
    -0.06
     will
    -0.06
    POSITIVE LOGITS
     جمع
    0.07
     Him
    0.07
    <Unit
    0.07
     Trotsky
    0.07
     ")"
    0.06
    toggle
    0.06
    xFF
    0.06
    /tasks
    0.06
     systemctl
    0.06
     अत
    0.06
    Act Density 0.023%

    No Known Activations