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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    semb
    -0.07
    -font
    -0.06
    .img
    -0.06
    holder
    -0.06
    공부
    -0.06
    (kv
    -0.06
    chimp
    -0.06
    .Date
    -0.06
    -wow
    -0.06
    бра
    -0.06
    POSITIVE LOGITS
    ']:↵
    0.07
    =Math
    0.06
     ),
↵
    0.06
     unexpectedly
    0.06
     BRA
    0.06
     |\
    0.06
    "]:↵
    0.06
    寸
    0.06
     bra
    0.06
    กรณ
    0.06
    Act Density 0.097%

    No Known Activations