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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and initialisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     test
    -0.07
     Reading
    -0.06
    fortune
    -0.06
     здоров
    -0.06
    wer
    -0.06
     Fletcher
    -0.06
    .Content
    -0.06
    <P
    -0.06
    _ITER
    -0.06
    _d
    -0.05
    POSITIVE LOGITS
     EntryPoint
    0.07
    Aug
    0.07
    kelas
    0.07
     ByteArrayOutputStream
    0.07
     rezerv
    0.07
    _produk
    0.06
     노
    0.06
     pests
    0.06
    -<?
    0.06
    
    0.06
    Act Density 0.002%

    No Known Activations