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

    Neuronpedia

    INDEX
    Explanations

    age differences in relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    僕
    -0.07
    (scores
    -0.06
    Yep
    -0.06
     Global
    -0.06
    .Foundation
    -0.06
    .good
    -0.06
    uba
    -0.06
     threw
    -0.06
     Toyota
    -0.06
    HM
    -0.06
    POSITIVE LOGITS
    buff
    0.07
    empresa
    0.07
    moth
    0.07
    toEqual
    0.06
    dat
    0.06
    Gr
    0.06
     congestion
    0.06
     piv
    0.06
     faç
    0.06
    олько
    0.06
    Act Density 0.199%

    No Known Activations