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

    Neuronpedia

    INDEX
    Explanations

    housing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jspx
    -0.07
     alike
    -0.07
    tif
    -0.07
    인터넷
    -0.07
     Chennai
    -0.07
    keh
    -0.07
    蕞
    -0.07
    翻开
    -0.07
     linspace
    -0.07
    HomeAsUpEnabled
    -0.06
    POSITIVE LOGITS
     licenses
    0.08
    (hidden
    0.07
    راح
    0.07
    造船
    0.07
    ⽴
    0.07
    /*.
    0.07
     ''↵
    0.07
     WC
    0.07
    ●
    0.07
     stabilization
    0.07
    Act Density 0.000%

    No Known Activations