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

    Neuronpedia

    INDEX
    Explanations

    something different or a twist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trials
    0.54
    trials
    0.50
     Trials
    0.48
     Trial
    0.47
    Trial
    0.45
    Trials
    0.45
     TRIAL
    0.44
     trial
    0.43
     ट्रायल
    0.42
     Bios
    0.38
    POSITIVE LOGITS
     difference
    1.67
    difference
    1.47
     Difference
    1.45
    Difference
    1.45
     diferença
    1.34
     différence
    1.32
     diferencia
    1.26
    差
    1.20
     differences
    1.20
     verschil
    1.16
    Act Density 0.019%

    No Known Activations