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

    Neuronpedia

    INDEX
    Explanations

    RRSP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worlds
    0.36
     link
    0.34
     pioneers
    0.34
     paragraphs
    0.33
     planets
    0.33
     proof
    0.32
     pann
    0.32
    営業時間
    0.32
     מק
    0.32
    コス
    0.31
    POSITIVE LOGITS
    Inactive
    0.36
     مدد
    0.36
    Jacob
    0.36
    Response
    0.35
    Plaintiff
    0.34
    ؟؟
    0.34
    狗狗
    0.34
     coordin
    0.33
    Participant
    0.33
    ග
    0.33
    Act Density 0.000%

    No Known Activations