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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    舺
    0.25
     ইহ
    0.24
    ipay
    0.24
    cvtColor
    0.24
    do
    0.24
    rstrip
    0.24
    ふ
    0.24
    qa
    0.23
     soweit
    0.23
    もある
    0.23
    POSITIVE LOGITS
     avenues
    0.29
     pathologists
    0.28
    🥊
    0.27
     финан
    0.27
     auditors
    0.27
    แต่ละ
    0.27
     ගන්න
    0.26
    👔
    0.26
    🗺
    0.26
     motivations
    0.26
    Act Density 0.651%

    No Known Activations