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

    Neuronpedia

    INDEX
    Explanations

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embodies
    -0.06
    .vm
    -0.06
     excuses
    -0.06
     situace
    -0.06
     Kunden
    -0.06
    ﻴ
    -0.06
     isn
    -0.06
     rivals
    -0.06
    Scheduled
    -0.06
    oksen
    -0.06
    POSITIVE LOGITS
    argar
    0.07
    CERT
    0.07
     staffing
    0.06
    Alpha
    0.06
     moderator
    0.06
    wechat
    0.06
    стра
    0.06
     greater
    0.06
    Veter
    0.06
     django
    0.06
    Act Density 0.001%

    No Known Activations