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

    Neuronpedia

    INDEX
    Explanations

    note down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handjob
    -0.08
    èn
    -0.07
     Crack
    -0.07
     takeover
    -0.06
     допом
    -0.06
     governments
    -0.06
    warz
    -0.06
    Born
    -0.06
    Τα
    -0.06
     Criterion
    -0.06
    POSITIVE LOGITS
    (effect
    0.07
    ultip
    0.06
     есте
    0.06
    ATRIX
    0.06
    udev
    0.06
    ('__
    0.06
    arası
    0.06
    	scanf
    0.06
    alist
    0.06
     acquitted
    0.06
    Act Density 0.023%

    No Known Activations