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

    Neuronpedia

    INDEX
    Explanations

    destruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mas
    -0.07
     CAST
    -0.07
     Ax
    -0.06
    anst
    -0.06
    tah
    -0.06
    Respons
    -0.06
    ujeme
    -0.06
    玉
    -0.06
    yla
    -0.06
     عن
    -0.06
    POSITIVE LOGITS
    -workers
    0.07
     overload
    0.07
     disks
    0.07
     barbecue
    0.06
     voters
    0.06
     Kawasaki
    0.06
    년
    0.06
     Гор
    0.06
     compartments
    0.06
     tartış
    0.06
    Act Density 0.012%

    No Known Activations