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

    Neuronpedia

    INDEX
    Explanations

    wishing well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Boom
    -0.07
     Livingston
    -0.07
    、三
    -0.07
     Philips
    -0.06
     Yosh
    -0.06
     任
    -0.06
    �
    -0.06
    átka
    -0.06
    Phil
    -0.06
     přísluš
    -0.06
    POSITIVE LOGITS
     {}
↵
    0.07
    execute
    0.06
     archived
    0.06
     end
    0.06
    next
    0.06
    INESS
    0.06
    _production
    0.06
     observed
    0.06
     ser
    0.06
    dit
    0.06
    Act Density 0.013%

    No Known Activations