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

    Neuronpedia

    INDEX
    Explanations

    Highways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     room
    -0.08
     dati
    -0.07
    -reported
    -0.07
     Robertson
    -0.07
     nc
    -0.07
     Sand
    -0.07
     mice
    -0.07
     �
    -0.06
     aging
    -0.06
     warmer
    -0.06
    POSITIVE LOGITS
     highway
    0.09
     Highway
    0.08
     highways
    0.08
    TEMP
    0.07
     freeway
    0.07
    幸
    0.06
    Visibility
    0.06
     Speedway
    0.06
    .MaximizeBox
    0.06
     shove
    0.06
    Act Density 0.006%

    No Known Activations