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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WM
    -0.07
    abort
    -0.06
    Sanders
    -0.06
    袋
    -0.06
    (validation
    -0.06
    Tyler
    -0.06
    ωμάτιο
    -0.06
     relentless
    -0.06
     Bulletin
    -0.06
     about
    -0.05
    POSITIVE LOGITS
    -syntax
    0.07
    \Notifications
    0.07
    貨
    0.07
    /respond
    0.06
    贫
    0.06
     біль
    0.06
    foreign
    0.06
    .ll
    0.06
    mín
    0.06
    ivals
    0.06
    Act Density 0.004%

    No Known Activations