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
    757
    -0.06
    olders
    -0.06
     Verg
    -0.06
    SEQU
    -0.06
    esper
    -0.06
     Everyday
    -0.06
    лон
    -0.06
    ---------↵
    -0.06
    NOT
    -0.06
    子は
    -0.06
    POSITIVE LOGITS
    =============
    0.08
    leDb
    0.07
     land
    0.07
     mView
    0.07
     fish
    0.07
    patients
    0.06
     питания
    0.06
    +'</
    0.06
    NodeType
    0.06
    loadModel
    0.06
    Act Density 0.002%

    No Known Activations