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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eighth
    -0.08
     nec
    -0.08
    Early
    -0.08
    作家
    -0.07
     Sche
    -0.07
     Early
    -0.07
    蜒
    -0.07
     Bog
    -0.07
     Niet
    -0.07
    .lot
    -0.07
    POSITIVE LOGITS
     ""));↵
    0.07
    Submitting
    0.07
     сит
    0.07
    笆
    0.07
     Stuff
    0.06
     snprintf
    0.06
    plus
    0.06
    stdbool
    0.06
    笼
    0.06
    컵
    0.06
    Act Density 0.008%

    No Known Activations