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

    Neuronpedia

    INDEX
    Explanations

    view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    EqualTo
    -0.07
    �
    -0.06
     duplic
    -0.06
    .SC
    -0.06
    _playlist
    -0.06
     Siber
    -0.06
    Manifest
    -0.06
     VC
    -0.06
     MISS
    -0.05
    POSITIVE LOGITS
     verbosity
    0.07
    Authorization
    0.06
    Monad
    0.06
    assume
    0.06
     outdoors
    0.06
     طلا
    0.06
    (fin
    0.06
    	word
    0.06
    iku
    0.06
    oodles
    0.06
    Act Density 0.000%

    No Known Activations