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

    Neuronpedia

    INDEX
    Explanations

    arty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -char
    -0.07
     –
    -0.07
    Dir
    -0.07
    udoku
    -0.06
     casi
    -0.06
    -submit
    -0.06
    -(
    -0.06
    ционный
    -0.06
     Attributes
    -0.06
    logfile
    -0.06
    POSITIVE LOGITS
     handy
    0.07
    .Focus
    0.06
    _Function
    0.06
     shady
    0.06
     çap
    0.06
     Ned
    0.06
    /request
    0.06
    ilerden
    0.06
    ')}}"
    0.05
     म
    0.05
    Act Density 0.088%

    No Known Activations