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

    Neuronpedia

    INDEX
    Explanations

    Stereotypes and negative perceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ш
    -0.07
    .est
    -0.07
     suppression
    -0.07
    墙
    -0.07
    oram
    -0.07
     passing
    -0.06
    vern
    -0.06
    夏
    -0.06
    -ball
    -0.06
     animated
    -0.06
    POSITIVE LOGITS
    NSUserDefaults
    0.06
    	Assert
    0.06
     JADX
    0.06
    845
    0.06
     setName
    0.06
    assertFalse
    0.06
     FedEx
    0.06
    \Lib
    0.06
    orative
    0.06
    Pixmap
    0.06
    Act Density 0.010%

    No Known Activations