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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    หลาย
    -0.08
     explicit
    -0.07
     Requirements
    -0.07
    (attribute
    -0.07
     expressions
    -0.07
    ASI
    -0.07
    มา
    -0.07
     Explicit
    -0.07
     Expressions
    -0.07
     Более
    -0.07
    POSITIVE LOGITS
     genießen
    0.08
     đang
    0.08
     buz
    0.08
     luncheon
    0.08
     tide
    0.08
     prosp
    0.08
     tonight
    0.08
    >>>>>>>>
    0.08
     fiestas
    0.08
     vandaag
    0.08
    Act Density 0.090%

    No Known Activations