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

    Neuronpedia

    INDEX
    Explanations

    Da

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of protein molecular weights (numbers followed by “kDa” or “Da”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    UD
    -0.07
    .orange
    -0.07
    .pose
    -0.06
     Vanguard
    -0.06
     Lost
    -0.06
    Pad
    -0.06
     SAT
    -0.06
     acne
    -0.06
     ye
    -0.06
    hodob
    -0.06
    POSITIVE LOGITS
    فاق
    0.07
    дии
    0.06
    643
    0.06
     Γ
    0.06
    ：「
    0.06
     капит
    0.06
     그가
    0.06
     {@
    0.06
    =min
    0.06
     многих
    0.06
    Act Density 0.012%

    No Known Activations