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

    Neuronpedia

    INDEX
    Explanations

    any claim or decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flavorful
    0.49
     Insights
    0.47
     μιας
    0.46
     insightful
    0.45
     norepinephrine
    0.45
     lackluster
    0.44
     Mechanisms
    0.44
    将被
    0.44
     perilaku
    0.43
     societal
    0.43
    POSITIVE LOGITS
     endeavour
    0.64
     endeavoured
    0.63
     practically
    0.61
    pract
    0.54
     satisfactory
    0.50
     utilised
    0.49
     actuated
    0.49
     definitely
    0.48
     favourably
    0.47
     realise
    0.47
    Act Density 0.001%

    No Known Activations