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

    Neuronpedia

    INDEX
    Explanations

    task management app names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spells
    0.46
    testimon
    0.39
     Mostly
    0.39
    ที่จะ
    0.38
    চিতে
    0.38
     blok
    0.38
    たちの
    0.38
    逡
    0.38
    ანა
    0.38
     discern
    0.37
    POSITIVE LOGITS
     Rom
    0.37
     tương
    0.36
     процен
    0.36
     কাত
    0.35
     معیار
    0.35
     Touchable
    0.34
     Din
    0.34
     पिंड
    0.33
     quantified
    0.33
    五十
    0.33
    Act Density 0.001%

    No Known Activations