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

    Neuronpedia

    INDEX
    Explanations

    mathematical and code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovators
    0.41
     pioneers
    0.35
     социально
    0.33
     inventions
    0.33
    บุคคล
    0.33
     वरिष्ठ
    0.33
    founders
    0.33
    invent
    0.32
     ingenuity
    0.32
     innovative
    0.32
    POSITIVE LOGITS
     Kedua
    0.39
    उनके
    0.37
     उसके
    0.36
     उनके
    0.36
     Two
    0.36
     svom
    0.36
     pInBuffer
    0.35
     ScriptInterface
    0.35
    もなく
    0.35
     Với
    0.34
    Act Density 0.053%

    No Known Activations