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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vu
    -0.07
     TAKE
    -0.07
     increased
    -0.06
    IEnumerable
    -0.06
     IPO
    -0.06
     tweak
    -0.06
    ěř
    -0.06
     intention
    -0.06
     postponed
    -0.06
    ";
↵
↵
    -0.06
    POSITIVE LOGITS
    čen
    0.07
    .flag
    0.07
     pits
    0.06
    reso
    0.06
     Pornhub
    0.06
    abus
    0.06
    .rollback
    0.06
     allotted
    0.06
    عمال
    0.06
    :invoke
    0.06
    Act Density 0.020%

    No Known Activations