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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енные
    -0.07
    compiler
    -0.07
    .SetParent
    -0.07
    CV
    -0.07
    ++]
    -0.06
     Grat
    -0.06
     incontri
    -0.06
     dai
    -0.06
    енных
    -0.06
     Lamb
    -0.06
    POSITIVE LOGITS
     Traffic
    0.07
     (#
    0.07
    承载
    0.07
     trafficking
    0.07
     softly
    0.07
     parcels
    0.07
    外贸
    0.07
     quartz
    0.07
    _application
    0.07
     DEF
    0.07
    Act Density 0.000%

    No Known Activations