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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рады
    -0.09
     défendre
    -0.08
     defending
    -0.08
    石
    -0.08
     �
    -0.08
     invented
    -0.08
    .enemy
    -0.08
     monopoly
    -0.08
     Gara
    -0.08
     defensor
    -0.08
    POSITIVE LOGITS
     bounded
    0.09
     integr
    0.08
     convergence
    0.08
    bounded
    0.08
    weighted
    0.08
     weighed
    0.08
     sufficient
    0.07
     भार
    0.07
    健
    0.07
     regularly
    0.07
    Act Density 0.005%

    No Known Activations