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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ISA
    -0.08
    is
    -0.07
     nose
    -0.07
    (angle
    -0.07
     ability
    -0.07
     І
    -0.07
     harga
    -0.07
     shirt
    -0.07
    Defense
    -0.07
    *I
    -0.07
    POSITIVE LOGITS
     them
    0.10
     Them
    0.08
     )
↵
    0.07
     BrowserAnimationsModule
    0.07
     ně
    0.07
    ेम
    0.06
     üzerinden
    0.06
    lords
    0.06
     //////////////////////////////////
    0.06
    ."↵↵↵↵
    0.06
    Act Density 0.068%

    No Known Activations