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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash

    This neuron activates on business-jargon terms describing value propositions and related “value” wording.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ignum
    -0.07
     recipe
    -0.07
    natal
    -0.06
     noir
    -0.06
     Pruitt
    -0.06
    ↵↵↵↵↵↵↵↵↵
    -0.06
     práva
    -0.06
    Knife
    -0.06
     �
    -0.06
     практи
    -0.06
    POSITIVE LOGITS
    ρισ
    0.07
     Value
    0.07
     располаг
    0.07
     lawyers
    0.07
     zm
    0.07
    рей
    0.07
     patented
    0.06
    .RowStyles
    0.06
     differentiated
    0.06
     사랑
    0.06
    Act Density 0.011%

    No Known Activations