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

    Neuronpedia

    INDEX
    Explanations

    losing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मे
    0.68
    тельные
    0.67
    urbance
    0.67
    тельными
    0.64
    urii
    0.63
     निवार
    0.63
    KeyboardMarkup
    0.62
     Dispute
    0.62
    icel
    0.62
    жнарод
    0.61
    POSITIVE LOGITS
     sight
    1.41
    sight
    1.22
     weight
    1.12
     Sight
    1.10
    weight
    1.07
    Sight
    0.95
     ground
    0.89
     momentum
    0.88
     traction
    0.87
     steam
    0.86
    Act Density 0.104%

    No Known Activations