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

    Neuronpedia

    INDEX
    Explanations

    -year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     permutation
    -0.08
    护身
    -0.08
     bruises
    -0.08
    .equalsIgnoreCase
    -0.08
     Bian
    -0.07
    悴
    -0.07
     Honolulu
    -0.07
    四位
    -0.07
     כס
    -0.07
    _pin
    -0.07
    POSITIVE LOGITS
    (Post
    0.07
    Friday
    0.07
    감
    0.07
     democrat
    0.07
    관
    0.07
    لال
    0.07
     declar
    0.07
    _predict
    0.07
    	ULONG
    0.06
    UNIT
    0.06
    Act Density 0.005%

    No Known Activations