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

    Neuronpedia

    INDEX
    Explanations

    Liquid mixing experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     λ
    -0.07
     ordinance
    -0.07
    -founder
    -0.07
     cite
    -0.07
    いう
    -0.06
     actions
    -0.06
     sitcom
    -0.06
     deposition
    -0.06
    weeney
    -0.06
    论文
    -0.06
    POSITIVE LOGITS
    (duration
    0.06
     TECH
    0.06
     lda
    0.06
    Eta
    0.06
    ;">
↵
    0.06
    _WEEK
    0.06
     　　 　
    0.06
     diversified
    0.06
    ்
    0.06
    �니다
    0.06
    Act Density 0.026%

    No Known Activations