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

    Neuronpedia

    INDEX
    Explanations

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ضم
    0.40
     Subsect
    0.40
    🍖
    0.39
    getFile
    0.39
     generalizing
    0.38
    된
    0.38
    📂
    0.37
    ToJson
    0.37
    滀
    0.36
    jsonify
    0.36
    POSITIVE LOGITS
     entered
    1.84
     enter
    1.73
     entering
    1.66
    entered
    1.61
     enters
    1.57
     Entered
    1.54
    Entered
    1.52
    输入
    1.45
     Entering
    1.44
     Enter
    1.42
    Act Density 0.041%

    No Known Activations