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

    Neuronpedia

    INDEX
    Explanations

    playful romantic utterances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ائع
    0.45
     अनेक
    0.44
    🙏🙏
    0.43
    近年
    0.43
    क्षित
    0.43
    Remain
    0.43
     !\
    0.42
     !}\
    0.42
    %!
    0.42
     !}{
    0.42
    POSITIVE LOGITS
     smirk
    0.63
     Boyfriend
    0.61
     bored
    0.59
     😘
    0.59
    😘
    0.58
     boyfriend
    0.58
     sweetheart
    0.57
     jealous
    0.56
     babe
    0.55
    💋
    0.54
    Act Density 0.024%

    No Known Activations