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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    boot
    -0.08
     crem
    -0.06
    AAA
    -0.06
    igroup
    -0.06
    (UI
    -0.06
     Tôi
    -0.06
    Work
    -0.06
    '></
    -0.06
    -trans
    -0.05
     ninguna
    -0.05
    POSITIVE LOGITS
    instanc
    0.07
     長
    0.07
    element
    0.07
    .getLogin
    0.07
     asn
    0.06
     eleven
    0.06
    547
    0.06
    .fromCharCode
    0.06
    .Parse
    0.06
    .Generation
    0.06
    Act Density 0.011%

    No Known Activations