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

    Neuronpedia

    INDEX
    Explanations

    any other questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     information
    0.52
     anything
    0.49
     clarification
    0.44
     Clar
    0.40
     Help
    0.40
    Help
    0.40
     informasjon
    0.40
     Information
    0.39
    信息
    0.39
     help
    0.38
    POSITIVE LOGITS
     FOLLOW
    0.49
    follow
    0.48
     follow
    0.47
     تابع
    0.43
    Follow
    0.43
    FOLLOW
    0.41
     followup
    0.40
    follows
    0.39
    フォロー
    0.38
     сле
    0.37
    Act Density 0.014%

    No Known Activations