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

    Neuronpedia

    INDEX
    Explanations

    lists of bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.55
    *
    0.54
    С
    0.51
    ווי
    0.48
    의
    0.46
    Фото
    0.46
    Ф
    0.46
    ла
    0.45
    :%
    0.45
    STAR
    0.44
    POSITIVE LOGITS
    <unused2017>
    0.48
    ೊಂಡು
    0.47
    কে
    0.44
    កាន់
    0.44
     pís
    0.44
    ní
    0.44
     思う
    0.44
    ěk
    0.42
    ë
    0.42
     soothing
    0.42
    Act Density 0.872%

    No Known Activations