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

    Neuronpedia

    INDEX
    Explanations

    company names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()))↵↵
    -0.06
     toll
    -0.06
     flush
    -0.06
     ke
    -0.06
     abbiamo
    -0.06
     eriş
    -0.06
     différentes
    -0.06
     tamb
    -0.06
     lyr
    -0.06
     pharmacist
    -0.06
    POSITIVE LOGITS
    .Warning
    0.08
    measurement
    0.07
    стров
    0.07
    solid
    0.06
     Charts
    0.06
     '.$
    0.06
     lucrative
    0.06
    LES
    0.06
     Cruise
    0.06
    ,cv
    0.06
    Act Density 0.146%

    No Known Activations