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

    Neuronpedia

    INDEX
    Explanations

    Software configuration/setup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feedback
    -0.07
     cognition
    -0.07
     function
    -0.07
     obey
    -0.07
     seized
    -0.06
     computed
    -0.06
     majestic
    -0.06
     xp
    -0.06
     vak
    -0.06
     tester
    -0.06
    POSITIVE LOGITS
    /Common
    0.07
    โซ
    0.07
    ักษณ
    0.06
    giene
    0.06
    _ro
    0.06
    udder
    0.06
    Tai
    0.06
    airie
    0.06
    ENOMEM
    0.06
    sans
    0.06
    Act Density 0.130%

    No Known Activations