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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     `,↵
    -0.06
    (save
    -0.06
    Storage
    -0.06
     received
    -0.06
    ažd
    -0.06
     telescope
    -0.05
     jewelry
    -0.05
    :↵↵↵↵
    -0.05
    рім
    -0.05
    á
    -0.05
    POSITIVE LOGITS
     Ngh
    0.07
     أمر
    0.07
    FillColor
    0.07
     Granted
    0.07
    olkata
    0.06
     negligible
    0.06
    .Dev
    0.06
     Mumbai
    0.06
     Ι
    0.06
     Dess
    0.06
    Act Density 0.006%

    No Known Activations