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

    Neuronpedia

    INDEX
    Explanations

    chapter section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oid
    -0.07
    .Drop
    -0.06
     lng
    -0.06
    阿
    -0.06
     Harvard
    -0.06
    _format
    -0.06
    Healthy
    -0.06
     trú
    -0.06
    ULATION
    -0.06
    ,
    -0.06
    POSITIVE LOGITS
     fierc
    0.06
     pale
    0.06
    죽
    0.06
    剂
    0.06
    Originally
    0.06
    -bedroom
    0.06
    现代
    0.06
     нез
    0.06
    ندق
    0.06
     зер
    0.06
    Act Density 0.059%

    No Known Activations