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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    하우
    -0.07
     Й
    -0.07
    яет
    -0.06
    анс
    -0.06
    vě
    -0.06
     weap
    -0.06
    лев
    -0.06
     YES
    -0.06
    ели
    -0.06
    JO
    -0.06
    POSITIVE LOGITS
     oceans
    0.07
    (infile
    0.06
     Dump
    0.06
    .HTML
    0.06
    .removeListener
    0.06
    ´:
    0.06
    ımın
    0.06
    .ie
    0.06
     한국
    0.06
    BOOK
    0.06
    Act Density 0.009%

    No Known Activations