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

    Neuronpedia

    INDEX
    Explanations

    technical code and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gosudarstvennyj
    0.52
     saber
    0.47
     turbidity
    0.47
    ℧
    0.46
    kBtu
    0.46
     barns
    0.45
     tantrums
    0.45
    kfollowers
    0.44
    শাসনের
    0.44
     craters
    0.44
    POSITIVE LOGITS
    на
    0.47
    а
    0.46
     Linux
    0.44
     डेविड
    0.44
     Padma
    0.42
     دریافت
    0.41
    ilya
    0.41
     Hindi
    0.41
    izing
    0.40
     використову
    0.40
    Act Density 0.143%

    No Known Activations