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

    Neuronpedia

    INDEX
    Explanations

    foreign banks and gorgeous people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FLU
    0.46
    㝡
    0.42
     Regan
    0.42
     Bolog
    0.41
    လား
    0.40
    ajal
    0.40
    Ղ
    0.39
     retinol
    0.39
    <unused1165>
    0.38
    ⌝
    0.38
    POSITIVE LOGITS
    umes
    0.39
    Byte
    0.39
    estra
    0.38
     sorted
    0.37
    Err
    0.37
    ാൻഡ്
    0.36
     deactivate
    0.36
     removes
    0.35
    Sorted
    0.35
    urr
    0.35
    Act Density 0.000%

    No Known Activations