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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aide
    -0.07
    בד
    -0.07
    diğiniz
    -0.06
    一颗
    -0.06
    ㌶
    -0.06
    arded
    -0.06
    ⇰
    -0.06
    嫒
    -0.06
    肤
    -0.06
     דעת
    -0.06
    POSITIVE LOGITS
    >';↵
    0.07
    关
    0.07
     blockade
    0.07
    ]'↵
    0.07
    𝚔
    0.07
    Mutation
    0.07
     Corinth
    0.07
     equalTo
    0.07
    opathy
    0.07
    Query
    0.07
    Act Density 0.003%

    No Known Activations