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

    Neuronpedia

    INDEX
    Explanations

    drive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     транс
    -0.06
     객
    -0.06
     chmod
    -0.06
    ительного
    -0.06
    .photos
    -0.06
     उद
    -0.06
    velop
    -0.06
    hir
    -0.06
    irmware
    -0.06
     dostup
    -0.06
    POSITIVE LOGITS
     driving
    0.07
     supports
    0.07
     dreaded
    0.07
     driven
    0.07
    rence
    0.07
     пят
    0.06
    requested
    0.06
     injected
    0.06
     Damen
    0.06
     feed
    0.06
    Act Density 0.006%

    No Known Activations