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

    Neuronpedia

    INDEX
    Explanations

    prompting reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tars
    0.40
     TAR
    0.40
     GBP
    0.40
     sigurn
    0.40
     NTE
    0.39
     ط
    0.39
    怖
    0.39
     tar
    0.38
     matter
    0.38
    ব্র
    0.38
    POSITIVE LOGITS
    舢
    0.39
    Unlimited
    0.39
    ekkür
    0.37
    hindi
    0.37
     продолжаем
    0.37
    的公司
    0.37
     meek
    0.37
    ajan
    0.36
     singers
    0.35
    herald
    0.35
    Act Density 0.000%

    No Known Activations