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

    Neuronpedia

    INDEX
    Explanations

    mainly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eskorte
    -0.07
    oden
    -0.07
     bunk
    -0.07
    ↵   ↵
    -0.07
    oksen
    -0.06
     lavoro
    -0.06
    izens
    -0.06
    ($"
    -0.06
    eko
    -0.06
     offending
    -0.06
    POSITIVE LOGITS
     mainly
    0.18
     primarily
    0.12
     chiefly
    0.11
     principalmente
    0.09
     principally
    0.09
    主要
    0.09
     mostly
    0.08
     Binder
    0.07
     başta
    0.07
     purely
    0.07
    Act Density 0.017%

    No Known Activations