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

    Neuronpedia

    INDEX
    Explanations

    associated with a purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Harald
    0.41
    磴
    0.39
     dynamics
    0.38
    dynamics
    0.38
     Dynamics
    0.38
    Auth
    0.38
     Auth
    0.37
     Tot
    0.37
     Haut
    0.37
     მათი
    0.37
    POSITIVE LOGITS
     несу
    0.45
    BMP
    0.41
    izzato
    0.40
     burdensome
    0.40
    URATION
    0.38
    ೋನ್
    0.38
     algebraically
    0.38
     препят
    0.36
     conlle
    0.36
     leichte
    0.36
    Act Density 0.001%

    No Known Activations