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

    Neuronpedia

    INDEX
    Explanations

    ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nth
    -0.07
    =r
    -0.07
    ToLeft
    -0.07
    	remove
    -0.06
     Casinos
    -0.06
    broken
    -0.06
     thích
    -0.06
     republik
    -0.06
     disgusted
    -0.06
     symbolic
    -0.06
    POSITIVE LOGITS
    doc
    0.06
    lhs
    0.06
     gmail
    0.06
    educt
    0.06
     chloride
    0.06
    TreeWidgetItem
    0.06
    ademic
    0.06
    (sess
    0.06
     amour
    0.06
     mitig
    0.06
    Act Density 0.004%

    No Known Activations