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

    Neuronpedia

    INDEX
    Explanations

    housing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foy
    -0.06
    宁
    -0.06
    alin
    -0.06
     zien
    -0.06
     DUP
    -0.06
     육
    -0.06
    apg
    -0.06
     Jal
    -0.06
    ख
    -0.06
     Gä
    -0.06
    POSITIVE LOGITS
     delet
    0.07
    (doc
    0.07
    .drop
    0.07
    查看摘要
    0.06
    _tickets
    0.06
    (default
    0.06
    사진
    0.06
    .As
    0.06
    	panel
    0.06
     beloved
    0.06
    Act Density 0.021%

    No Known Activations