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

    Neuronpedia

    INDEX
    Explanations

    Deals and signings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Declaration
    -0.07
    art
    -0.07
    posed
    -0.06
    _assignment
    -0.06
    	counter
    -0.06
    \M
    -0.06
    Turn
    -0.06
    .annotation
    -0.06
    Fullscreen
    -0.06
    守
    -0.06
    POSITIVE LOGITS
     civilian
    0.06
    cion
    0.06
    ópez
    0.06
    umni
    0.06
     kişisel
    0.06
    틀
    0.06
    }_${
    0.06
     фев
    0.06
    ('{{
    0.06
    issy
    0.06
    Act Density 0.038%

    No Known Activations