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

    Neuronpedia

    INDEX
    Explanations

    curious boys, during sex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uler
    0.40
    evre
    0.38
     reconhe
    0.38
    驗
    0.38
    ahu
    0.38
    ুক্ত
    0.37
     excellente
    0.37
    XO
    0.36
    สวย
    0.36
    峴
    0.36
    POSITIVE LOGITS
    pertoire
    0.40
     twigs
    0.39
     quoted
    0.39
     Mantra
    0.38
     appropriateness
    0.38
     नतीजे
    0.37
     bör
    0.36
     относи
    0.36
    quoted
    0.35
    InCM
    0.35
    Act Density 0.185%

    No Known Activations