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

    Neuronpedia

    INDEX
    Explanations

    especially

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .disconnect
    -0.07
    .dy
    -0.07
    .jquery
    -0.07
    pickle
    -0.07
    xec
    -0.07
    elcome
    -0.07
     nerve
    -0.07
     Restrictions
    -0.06
     lodged
    -0.06
     WINDOWS
    -0.06
    POSITIVE LOGITS
    (phi
    0.07
    byter
    0.07
    _empresa
    0.07
    主动性
    0.07
     oils
    0.07
    Idx
    0.07
    _cliente
    0.07
    独特
    0.07
     Company
    0.06
     baru
    0.06
    Act Density 0.013%

    No Known Activations