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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parses
    -0.07
    click
    -0.07
    .CH
    -0.07
    sec
    -0.07
    _js
    -0.07
    intro
    -0.07
    .xyz
    -0.07
    _now
    -0.06
     kidnapped
    -0.06
    нак
    -0.06
    POSITIVE LOGITS
    褕
    0.07
     worth
    0.07
    doubleValue
    0.07
     agenda
    0.06
    ｝
    0.06
     фор
    0.06
    ework
    0.06
     fisheries
    0.06
     создан
    0.06
    uir
    0.06
    Act Density 0.001%

    No Known Activations