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

    Neuronpedia

    INDEX
    Explanations

    rude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羅
    -0.07
     FRA
    -0.06
    _finished
    -0.06
     vlád
    -0.06
     insurers
    -0.06
     canned
    -0.06
     propos
    -0.06
    Louis
    -0.06
    .CG
    -0.06
    фіка
    -0.05
    POSITIVE LOGITS
     şans
    0.08
     rude
    0.07
     lassen
    0.07
     indirectly
    0.07
    ******↵↵
    0.07
     Indians
    0.07
     ************************
    0.06
     intValue
    0.06
     inadvertently
    0.06
    .navigate
    0.06
    Act Density 0.013%

    No Known Activations