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

    Neuronpedia

    INDEX
    Explanations

    user commands and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ab
    0.52
    copies
    0.45
    ды
    0.44
    Matt
    0.44
    }-$
    0.44
    アイテム
    0.44
    kinase
    0.44
    M
    0.44
     соединения
    0.44
    トン
    0.43
    POSITIVE LOGITS
     claims
    0.53
     tic
    0.52
     XC
    0.49
     digitally
    0.46
     terminology
    0.46
     Doch
    0.45
     dog
    0.44
     imagery
    0.44
     wording
    0.44
     במש
    0.43
    Act Density 0.001%

    No Known Activations