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

    Neuronpedia

    INDEX
    Explanations

    election candidates and compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    체를
    0.42
    implicitly
    0.39
    implicit
    0.38
    Implicit
    0.38
    ï
    0.37
     சேர்த்த
    0.36
    most
    0.36
     horm
    0.36
     thể
    0.35
     implicitly
    0.35
    POSITIVE LOGITS
    Compliance
    0.46
     Compliance
    0.44
    휼
    0.43
     compliance
    0.41
     Deborah
    0.41
    CubeSize
    0.41
     Trenton
    0.41
    畨
    0.41
     کراچی
    0.40
    တယ်။
    0.40
    Act Density 0.005%

    No Known Activations