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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .il
    -0.07
     THPT
    -0.06
    (par
    -0.06
    applicant
    -0.06
    ru
    -0.06
     PLC
    -0.06
    _m
    -0.06
    Pes
    -0.06
    Rob
    -0.06
    Items
    -0.06
    POSITIVE LOGITS
     действ
    0.07
     هذه
    0.07
     substant
    0.07
    utta
    0.06
     Jewel
    0.06
    ประโย
    0.06
     Terror
    0.06
    RowAnimation
    0.06
     пла
    0.06
     stringBuilder
    0.06
    Act Density 0.053%

    No Known Activations