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

    Neuronpedia

    INDEX
    Explanations

    dé

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bishops
    -0.07
    _reduction
    -0.07
    soever
    -0.07
     Vik
    -0.07
     charm
    -0.07
    브
    -0.07
    (getResources
    -0.07
    잪
    -0.06
    <Project
    -0.06
    сос
    -0.06
    POSITIVE LOGITS
     repertoire
    0.08
     descriptions
    0.08
    (EX
    0.07
    との
    0.07
    ambiguous
    0.07
     plotted
    0.07
     incremented
    0.07
     accurately
    0.07
    쁜
    0.07
     uncertainties
    0.07
    Act Density 0.021%

    No Known Activations