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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highlighted
    -0.07
    \uB
    -0.06
    rance
    -0.06
    낍
    -0.06
    	T
    -0.06
    ߕ
    -0.06
    씐
    -0.06
    ulner
    -0.06
    نسي
    -0.06
    健
    -0.06
    POSITIVE LOGITS
     measurable
    0.08
    öh
    0.07
    #/
    0.07
     stays
    0.06
    oned
    0.06
     premiums
    0.06
    .tight
    0.06
     Thom
    0.06
    _added
    0.06
    testing
    0.06
    Act Density 0.000%

    No Known Activations