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

    Neuronpedia

    INDEX
    Explanations

    abstract services or communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berbagai
    0.55
    Various
    0.53
    様々な
    0.50
     verschiedene
    0.48
     ulike
    0.48
    various
    0.48
    さまざまな
    0.48
    各种
    0.48
     различни
    0.47
    色々
    0.47
    POSITIVE LOGITS
     interactions
    0.63
     correspondence
    0.62
     communications
    0.62
     transactions
    0.62
     decisions
    0.57
     proceedings
    0.57
     communication
    0.55
     purchases
    0.55
     actions
    0.54
     Transactions
    0.54
    Act Density 0.014%

    No Known Activations