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

    Neuronpedia

    INDEX
    Explanations

    patrol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ูง
    -0.08
    _FIRE
    -0.07
    าคา
    -0.07
     mujeres
    -0.07
     insane
    -0.07
    cosa
    -0.07
     nikdo
    -0.07
     yyn
    -0.06
    积
    -0.06
     людина
    -0.06
    POSITIVE LOGITS
     patrol
    0.11
     Patrol
    0.10
     patrols
    0.08
     Scout
    0.07
     scouts
    0.07
    reach
    0.07
     scout
    0.07
     densities
    0.06
     escorts
    0.06
    brook
    0.06
    Act Density 0.005%

    No Known Activations