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

    Neuronpedia

    INDEX
    Explanations

    pathway

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    686
    -0.07
    Controller
    -0.06
    United
    -0.06
    imals
    -0.06
    rowable
    -0.06
    frican
    -0.06
     verified
    -0.06
    estimate
    -0.06
    800
    -0.06
     assassin
    -0.06
    POSITIVE LOGITS
     Lane
    0.08
     عقد
    0.07
     pathway
    0.07
     Hayden
    0.07
     waypoints
    0.07
    サイ
    0.07
     partnership
    0.07
     полос
    0.07
     lane
    0.07
     disreg
    0.07
    Act Density 0.006%

    No Known Activations