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

    Neuronpedia

    INDEX
    Explanations

    are you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imar
    0.48
    亠
    0.40
     ম্যাচের
    0.39
     matcher
    0.39
    Coleman
    0.38
     stmt
    0.38
     matchup
    0.38
    ataan
    0.37
     പിന്നീ
    0.37
     ম্যাচ
    0.37
    POSITIVE LOGITS
    5
    0.37
    కె
    0.37
    impossible
    0.36
    Actually
    0.36
    Anonymous
    0.36
    massage
    0.35
    You
    0.35
    ισμό
    0.35
    ስ
    0.35
    ඇ
    0.34
    Act Density 0.000%

    No Known Activations