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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    biên
    -0.07
    Bern
    -0.06
     Jaguars
    -0.06
    .br
    -0.06
     mluv
    -0.06
     incredibly
    -0.06
    éal
    -0.06
    emies
    -0.06
    /testify
    -0.06
    ekten
    -0.06
    POSITIVE LOGITS
    .slice
    0.06
     SMS
    0.06
    .pdf
    0.06
     tapes
    0.06
    .Scan
    0.06
     livelihood
    0.06
    .Ass
    0.06
    .Exists
    0.06
    ,password
    0.06
    .Drop
    0.06
    Act Density 0.012%

    No Known Activations