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

    Neuronpedia

    INDEX
    Explanations

    Screenwriting format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acknowledgment
    -0.09
    Acknowled
    -0.08
    ावर
    -0.08
    ük
    -0.08
     acknowledge
    -0.08
     Ehr
    -0.08
     acknowledgement
    -0.08
     acknowledging
    -0.08
    -Ar
    -0.08
     acknowledged
    -0.08
    POSITIVE LOGITS
     hereby
    0.11
     SCREEN
    0.11
     DIGITAL
    0.10
    SCREEN
    0.09
     SYSTEM
    0.09
     GENERAL
    0.09
    .Screen
    0.08
     HERE
    0.08
     ഡയറ
    0.08
     രംഗ
    0.08
    Act Density 0.056%

    No Known Activations