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

    Neuronpedia

    INDEX
    Explanations

    a lot of nuance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    銭
    0.45
     martens
    0.45
     preprocess
    0.44
     infl
    0.44
     août
    0.44
     yếu
    0.44
     faiblement
    0.43
     স্থানান্তর
    0.43
     boreal
    0.42
     être
    0.42
    POSITIVE LOGITS
    ee
    0.46
    piration
    0.45
    ern
    0.44
    Questions
    0.44
    ion
    0.43
    iss
    0.43
    UserModel
    0.43
    ai
    0.43
    ik
    0.43
    sa
    0.43
    Act Density 0.010%

    No Known Activations