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

    Neuronpedia

    INDEX
    Explanations

    comparing past and present

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ープ
    -0.07
     weitere
    -0.07
    颠覆
    -0.06
    rogen
    -0.06
    ,input
    -0.06
    튭
    -0.06
    wick
    -0.06
    경제
    -0.06
     Room
    -0.06
    أفكار
    -0.06
    POSITIVE LOGITS
    튱
    0.08
    Love
    0.07
    蓂
    0.07
     feed
    0.07
    ;
↵
↵
    0.07
     ping
    0.07
     fils
    0.07
    .bill
    0.06
     Kick
    0.06
    ጵ
    0.06
    Act Density 0.027%

    No Known Activations