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

    Neuronpedia

    INDEX
    Explanations

    Organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     constrained
    -0.07
     Cou
    -0.07
    _PID
    -0.07
    Gs
    -0.06
     milieu
    -0.06
     forbidden
    -0.06
     gi
    -0.06
     runner
    -0.06
    VIC
    -0.06
     halk
    -0.06
    POSITIVE LOGITS
    ksam
    0.07
    ("'",
    0.06
     yabancı
    0.06
     unitOfWork
    0.06
    НИ
    0.06
     ayr
    0.06
    Mailer
    0.06
    erald
    0.06
     вещества
    0.06
    َح
    0.06
    Act Density 0.021%

    No Known Activations