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

    Neuronpedia

    INDEX
    Explanations

    dying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     languid
    -1.04
    啥
    -1.04
    lla
    -1.03
    偷偷
    -1.01
     плана
    -1.01
    dom
    -1.00
     jenes
    -1.00
     deft
    -0.99
     .
    -0.99
    神
    -0.96
    POSITIVE LOGITS
     of
    1.46
     from
    1.22
     young
    1.15
    toronto
    1.04
    dede
    1.03
     in
    1.02
     because
    1.02
     Editora
    1.00
    💞
    0.99
    💅
    0.99
    Act Density 0.010%

    No Known Activations