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

    Neuronpedia

    INDEX
    Explanations

    mechanisms, principles, and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     streamlined
    0.41
     firsthand
    0.37
    wood
    0.36
    backward
    0.35
     K
    0.35
    mathemat
    0.35
     which
    0.34
     schools
    0.34
    ственные
    0.34
     self
    0.34
    POSITIVE LOGITS
    般的
    0.46
    ของการ
    0.46
    នៃ
    0.42
    式的
    0.42
     بشأن
    0.40
     mentality
    0.40
    owość
    0.39
     terhadap
    0.39
    十足
    0.38
     گونه
    0.38
    Act Density 0.019%

    No Known Activations