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

    Neuronpedia

    INDEX
    Explanations

    reaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sü
    -0.10
     aktu
    -0.08
     sacrifices
    -0.08
     sacrifice
    -0.08
     voorlopig
    -0.08
    abolism
    -0.08
    Experiment
    -0.08
    Ped
    -0.08
     kò
    -0.08
    Peace
    -0.07
    POSITIVE LOGITS
     পৌঁ
    0.13
     എത്ത
    0.13
     penetrate
    0.11
     inaccessible
    0.11
     eriş
    0.10
     проник
    0.10
     penetration
    0.10
     reachable
    0.10
     પહોંચી
    0.10
     पहुंच
    0.10
    Act Density 0.022%

    No Known Activations