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

    Neuronpedia

    INDEX
    Explanations

    code copyright notices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ......
    -0.07
    そのため
    -0.07
    _#{
    -0.07
     ign
    -0.07
    .f
    -0.07
    \API
    -0.07
    毅然
    -0.07
     itching
    -0.06
     Landscape
    -0.06
    转弯
    -0.06
    POSITIVE LOGITS
    级
    0.07
    (product
    0.07
    븅
    0.07
    HDR
    0.07
    getti
    0.07
    곂
    0.07
    —↵↵
    0.07
    ResultsController
    0.07
    ⼋
    0.07
     parties
    0.07
    Act Density 0.016%

    No Known Activations