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

    Neuronpedia

    INDEX
    Explanations

    says probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     n
    0.47
     it
    0.46
     tiktok
    0.45
     can
    0.44
     facilitates
    0.44
     people
    0.43
     integration
    0.43
    เฉพาะ
    0.43
     referral
    0.43
     private
    0.42
    POSITIVE LOGITS
    Completed
    0.51
    merz
    0.49
    ärke
    0.43
    Earnings
    0.42
    Percent
    0.42
    FOLD
    0.41
    Grade
    0.41
     čin
    0.41
     чувство
    0.41
    可谓
    0.41
    Act Density 0.005%

    No Known Activations