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

    Neuronpedia

    INDEX
    Explanations

    listing research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.44
    6
    0.43
    3
    0.38
    दिशा
    0.37
    ється
    0.35
    "*
    0.35
    <start_of_image>
    0.35
     assembling
    0.35
    <u>
    0.34
     away
    0.34
    POSITIVE LOGITS
    𒇷
    0.41
    TGFuZ
    0.39
     生命周期
    0.39
    Mutability
    0.39
     متع
    0.38
    HeaderText
    0.38
     ቲ
    0.38
     הז
    0.37
    ")',
    0.37
    وزر
    0.37
    Act Density 0.000%

    No Known Activations