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

    Neuronpedia

    INDEX
    Explanations

    initiating descriptions or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كون
    0.42
     answers
    0.40
    celand
    0.39
     ơn
    0.38
     Answers
    0.37
    inkl
    0.36
     Elton
    0.36
     الول
    0.35
     page
    0.35
     inflation
    0.35
    POSITIVE LOGITS
    Compute
    0.47
    File
    0.46
    This
    0.45
    Dist
    0.42
    🤗
    0.41
    Calculate
    0.41
    IO
    0.41
    Pipeline
    0.41
    PRO
    0.41
    ヤ
    0.41
    Act Density 0.000%

    No Known Activations