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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生产工艺
    -0.08
    +Sans
    -0.07
    𝚁
    -0.07
    Tek
    -0.07
    饸
    -0.07
    工序
    -0.07
     guy
    -0.07
    ܘ
    -0.07
    رك
    -0.07
    kor
    -0.06
    POSITIVE LOGITS
    .AP
    0.08
     Mine
    0.07
    $http
    0.07
    _BACKGROUND
    0.07
    instead
    0.07
    がある
    0.07
     girlfriends
    0.07
     explained
    0.07
    =train
    0.07
    explained
    0.07
    Act Density 0.194%

    No Known Activations