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

    Neuronpedia

    INDEX
    Explanations

    Autobiographical/personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Responsive
    -0.07
     Freddy
    -0.06
    .Long
    -0.06
     {}));↵
    -0.06
     overview
    -0.06
     olarak
    -0.06
     hä
    -0.06
    649
    -0.06
     Scot
    -0.06
     Girlfriend
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Thema
    0.06
     busty
    0.06
     sollten
    0.06
     rude
    0.06
    zí
    0.06
    道路
    0.06
    gere
    0.06
    ѕ
    0.06
    	db
    0.06
    Act Density 0.029%

    No Known Activations