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

    Neuronpedia

    INDEX
    Explanations

    improved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ā
    -0.06
     Blow
    -0.06
    �
    -0.06
     karma
    -0.06
    ambique
    -0.06
    .borderColor
    -0.06
    bard
    -0.06
    ()↵
    -0.06
     نش
    -0.06
     svém
    -0.05
    POSITIVE LOGITS
    _Do
    0.07
    monkey
    0.07
    до
    0.07
    WithContext
    0.07
    (customer
    0.06
     localObject
    0.06
     بالم
    0.06
    (',
    0.06
     siyas
    0.06
     newPassword
    0.06
    Act Density 0.011%

    No Known Activations