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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    10
    -0.08
    75
    -0.07
    -band
    -0.07
    85
    -0.07
     ml
    -0.07
    	ID
    -0.07
    Diff
    -0.07
     Lamb
    -0.07
    _up
    -0.07
    120
    -0.07
    POSITIVE LOGITS
    :
    0.13
     :
    0.11
    ):
    0.09
     ):↵↵
    0.08
    ():
    0.08
    :A
    0.07
    ा:
    0.07
    :M
    0.07
    :↵↵
    0.07
    decrypt
    0.07
    Act Density 0.030%

    No Known Activations