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

    Neuronpedia

    INDEX
    Explanations

    historical periods and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }:{
    0.42
     энер
    0.41
    ্লাই
    0.40
     ribbed
    0.40
     BELL
    0.40
    院校
    0.40
    hoo
    0.39
    臓
    0.39
    coral
    0.39
    ণাস্ত্র
    0.39
    POSITIVE LOGITS
     Kingdom
    0.46
    ım
    0.44
     Seek
    0.44
    Kingdom
    0.44
    کس
    0.43
    об
    0.42
     income
    0.42
    கா
    0.42
    চিতে
    0.42
    ரிய
    0.42
    Act Density 0.000%

    No Known Activations