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

    Neuronpedia

    INDEX
    Explanations

    counsel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vili
    0.84
    zó
    0.83
    €”
    0.83
    arono
    0.80
    ویں
    0.79
     جنيه
    0.77
    ộ
    0.77
    裡
    0.77
    ména
    0.77
     joy
    0.76
    POSITIVE LOGITS
    𝘪
    0.96
    𝘩
    0.90
    ت
    0.89
    𝘰
    0.89
    Eagle
    0.86
    с
    0.82
    𝐪
    0.81
     jazdy
    0.81
    𝐨
    0.78
     скорее
    0.77
    Act Density 0.001%

    No Known Activations