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

    Neuronpedia

    INDEX
    Explanations

    environmental protection policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فرق
    0.39
    atisf
    0.37
     losers
    0.36
     relatable
    0.36
    atschapp
    0.36
     بنا
    0.36
    ավ
    0.35
    ్యం
    0.35
    标准化
    0.35
    啕
    0.35
    POSITIVE LOGITS
     APC
    0.42
    unlist
    0.38
    APC
    0.37
    stift
    0.37
     tissue
    0.36
    ジア
    0.36
    Kit
    0.35
     আগুন
    0.35
    grow
    0.34
     эм
    0.34
    Act Density 0.000%

    No Known Activations