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

    Neuronpedia

    INDEX
    Explanations

    references and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JsonIgnore
    -0.07
     sigma
    -0.06
    _bitmap
    -0.06
    267
    -0.06
     lesb
    -0.06
    cı
    -0.06
    numer
    -0.06
     Эти
    -0.06
    asının
    -0.06
     Bu
    -0.06
    POSITIVE LOGITS
     BSP
    0.07
    _IMPORT
    0.06
     rather
    0.06
    Initial
    0.06
     MAD
    0.06
     看
    0.06
     =================================================================
    0.06
    .edit
    0.06
    oe
    0.06
    opher
    0.06
    Act Density 0.004%

    No Known Activations