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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Common
    -0.07
    แสดง
    -0.07
    €�
    -0.07
    SL
    -0.07
    .Cl
    -0.07
    Append
    -0.06
    σμού
    -0.06
    Permanent
    -0.06
     foresee
    -0.06
     acknowled
    -0.06
    POSITIVE LOGITS
    (activity
    0.07
     граф
    0.07
    ーチ
    0.06
    	perror
    0.06
    �
    0.06
    /on
    0.06
    rys
    0.06
    [tid
    0.06
    (Property
    0.06
    =length
    0.06
    Act Density 0.000%

    No Known Activations