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

    Neuronpedia

    INDEX
    Explanations

    geometry line intersections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ultras
    -0.08
     সাম
    -0.08
     Management
    -0.08
     עולה
    -0.07
     سہ
    -0.07
    mart
    -0.07
     downloaded
    -0.07
     Norfolk
    -0.07
     manganese
    -0.07
     feared
    -0.07
    POSITIVE LOGITS
     eventualmente
    0.09
     sooner
    0.09
     કરશે
    0.09
     eventually
    0.09
     llegará
    0.09
     termination
    0.09
     koń
    0.08
     prochaine
    0.08
     eventual
    0.08
    _exit
    0.08
    Act Density 0.040%

    No Known Activations