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

    Neuronpedia

    INDEX
    Explanations

    google.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </b>
    -3.55
     The
    -2.50
    ↵↵
    -2.44
    h
    -2.44
     to
    -2.41
     I
    -2.31
     is
    -2.30
     you
    -2.27
     de
    -2.19
     herhangi
    -2.14
    POSITIVE LOGITS
    禩
    2.88
    酲
    2.75
    2.72
    熜
    2.67
     油画
    2.59
     花朵
    2.56
    ⡪
    2.56
     cláss
    2.55
    نوع
    2.50
    ١
    2.50
    Act Density 0.009%

    No Known Activations