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

    Neuronpedia

    INDEX
    Explanations

    博弈

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trataro
    0.39
    🫤
    0.38
     NodeRef
    0.38
    sendKeyDown
    0.36
    reflectionMap
    0.36
    𐰆
    0.35
    🥸
    0.35
    VertexBuffer
    0.34
     entrees
    0.34
     myArray
    0.34
    POSITIVE LOGITS
     hedge
    0.37
    hot
    0.33
    ----------------
    0.32
    行人
    0.32
    CT
    0.31
     basically
    0.31
    有效
    0.31
     सत्य
    0.31
    Basically
    0.30
     நேரத்தில்
    0.30
    Act Density 0.000%

    No Known Activations