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

    Neuronpedia

    INDEX
    Explanations

    figure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     c
    -0.07
     Identify
    -0.07
     attending
    -0.07
    想不到
    -0.07
     aktuellen
    -0.07
    第三届
    -0.07
     extend
    -0.07
     passed
    -0.07
    зн
    -0.07
    Ｂ
    -0.07
    POSITIVE LOGITS
     Lowest
    0.07
    -Benz
    0.07
    zos
    0.06
    �
    0.06
     seab
    0.06
    ATTLE
    0.06
     Yoga
    0.06
     datum
    0.06
    积极作用
    0.06
     наибол
    0.06
    Act Density 0.015%

    No Known Activations