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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Allowed
    -0.07
    rottle
    -0.06
    角色
    -0.06
    衛
    -0.06
    aside
    -0.06
    秘
    -0.06
     tn
    -0.06
    istance
    -0.06
    payer
    -0.06
    gnore
    -0.06
    POSITIVE LOGITS
     />'
    0.08
     NSMutable
    0.08
     bif
    0.07
     εκ
    0.07
     SIG
    0.07
    .timestamp
    0.06
    (top
    0.06
     Stard
    0.06
    .SpringBootTest
    0.06
    \Abstract
    0.06
    Act Density 0.024%

    No Known Activations