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

    Neuronpedia

    INDEX
    Explanations

    international news/politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芯
    -0.06
    激动
    -0.06
    それは
    -0.06
    "display
    -0.06
     Sweat
    -0.06
    机器
    -0.06
     favourite
    -0.06
    𓅺
    -0.06
    ớ
    -0.06
    elier
    -0.06
    POSITIVE LOGITS
     prominently
    0.08
     hired
    0.07
     Holmes
    0.07
    за
    0.07
     setUsername
    0.07
     mins
    0.07
     reun
    0.07
    燕
    0.07
    桓
    0.07
    .boolean
    0.07
    Act Density 0.047%

    No Known Activations