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

    Neuronpedia

    INDEX
    Explanations

    .org organizations providing help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    欲しい
    0.41
    သွယ်
    0.39
     AliExpress
    0.38
     અલગ
    0.38
    Saver
    0.37
     respectively
    0.36
    之一
    0.36
     AWS
    0.36
     attribute
    0.35
     plank
    0.35
    POSITIVE LOGITS
    Provides
    0.86
     provides
    0.84
     Provides
    0.84
     fornisce
    0.73
    provides
    0.70
     fornece
    0.66
     предоставляет
    0.65
     biedt
    0.63
     bietet
    0.62
     oferece
    0.60
    Act Density 0.002%

    No Known Activations