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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    久
    -0.07
    partment
    -0.07
    Corp
    -0.07
    .sb
    -0.07
    omedical
    -0.07
    🍛
    -0.07
     prototype
    -0.07
     zwyk
    -0.07
    移到
    -0.07
    茫茫
    -0.07
    POSITIVE LOGITS
    subscriber
    0.07
    要求
    0.07
    .extension
    0.07
    ัน
    0.07
    赢得了
    0.07
     favourite
    0.07
    ]++;↵
    0.06
    ystone
    0.06
    OUNTRY
    0.06
    !');↵
    0.06
    Act Density 0.002%

    No Known Activations