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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ickými
    -0.07
     WCS
    -0.07
    xic
    -0.06
    _BP
    -0.06
     wrong
    -0.06
     학
    -0.06
     benöt
    -0.06
     Tabs
    -0.06
     Fs
    -0.06
     restrain
    -0.06
    POSITIVE LOGITS
    -kind
    0.07
    ").↵
    0.07
     Hin
    0.07
     floppy
    0.07
     affection
    0.06
    .putInt
    0.06
     prospect
    0.06
    encent
    0.06
    perimental
    0.06
    	EXPECT
    0.06
    Act Density 0.000%

    No Known Activations