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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лено
    -0.07
    的一个
    -0.07
     legalization
    -0.07
    ocus
    -0.07
    rc
    -0.07
     prost
    -0.07
    러리
    -0.06
    dro
    -0.06
     teslim
    -0.06
     agitation
    -0.06
    POSITIVE LOGITS
    Rotate
    0.06
     inexp
    0.06
     Bip
    0.06
     mainAxisAlignment
    0.06
    持
    0.06
     Composer
    0.06
     KeyboardInterrupt
    0.06
     saison
    0.06
     SNAP
    0.06
     grap
    0.06
    Act Density 0.002%

    No Known Activations