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

    Neuronpedia

    INDEX
    Explanations

    generated creative content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //$
    0.38
    OCT
    0.38
     벗
    0.38
     সড়
    0.37
    setProgress
    0.37
     basa
    0.37
    тт
    0.36
    ="<?=
    0.35
    毫米
    0.35
    ittet
    0.35
    POSITIVE LOGITS
     refrained
    0.48
     restrained
    0.39
     posters
    0.38
     upcoming
    0.37
    🏾
    0.36
     Aliment
    0.36
     thin
    0.36
    ensory
    0.36
    ğun
    0.36
     daily
    0.35
    Act Density 0.000%

    No Known Activations