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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Initially
    -0.07
    營
    -0.06
     grandfather
    -0.06
    opoly
    -0.06
     Analysis
    -0.06
    вано
    -0.06
     breakthrough
    -0.06
    ancel
    -0.06
     firstly
    -0.06
    -*
    -0.06
    POSITIVE LOGITS
     dictator
    0.07
    _REMOVE
    0.06
     पढ़
    0.06
     Střed
    0.06
    .setBackgroundColor
    0.06
     الوص
    0.06
    .dateFormat
    0.06
    :flutter
    0.06
     Jazz
    0.06
    -packed
    0.06
    Act Density 0.001%

    No Known Activations