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

    Neuronpedia

    INDEX
    Explanations

    latter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tony
    -0.07
     contest
    -0.07
     amp
    -0.07
     playground
    -0.06
    .activities
    -0.06
     usable
    -0.06
    iqu
    -0.06
    Opt
    -0.06
    	Simple
    -0.06
    Вы
    -0.06
    POSITIVE LOGITS
     latter
    0.11
    LOSE
    0.07
    afka
    0.07
    AR
    0.06
     shutil
    0.06
    .wrapper
    0.06
    ixon
    0.06
    \System
    0.06
    atter
    0.06
    Prior
    0.06
    Act Density 0.004%

    No Known Activations