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

    Neuronpedia

    INDEX
    Explanations

    current events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destiny
    -0.07
    ]"↵
    -0.07
    }}"↵
    -0.06
    ovable
    -0.06
    做得
    -0.06
    _mono
    -0.06
    称为
    -0.06
     obe
    -0.06
    =t
    -0.06
    弢
    -0.06
    POSITIVE LOGITS
     Chicken
    0.07
     Historic
    0.07
    你知道
    0.07
     Assassin
    0.07
    คาร
    0.07
    一刀
    0.06
     Vanessa
    0.06
     McGr
    0.06
    👎
    0.06
    媓
    0.06
    Act Density 0.349%

    No Known Activations