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

    Neuronpedia

    INDEX
    Explanations

    focus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ici
    -0.07
    ,Object
    -0.06
    .Window
    -0.06
    ////
    -0.06
     jour
    -0.06
    âh
    -0.06
    iminal
    -0.06
    ième
    -0.06
    .Handle
    -0.06
    Dispatch
    -0.06
    POSITIVE LOGITS
    거래
    0.07
     رشته
    0.07
     Rosenberg
    0.06
    .toCharArray
    0.06
     sağlık
    0.06
    责任
    0.06
     Anglo
    0.06
     resultMap
    0.06
    รว
    0.06
     samsung
    0.06
    Act Density 0.030%

    No Known Activations