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

    Neuronpedia

    INDEX
    Explanations

    competence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reflected
    -0.08
     air
    -0.07
     news
    -0.07
     тради
    -0.07
     Mail
    -0.07
     gamers
    -0.07
     illustrations
    -0.07
    ARRY
    -0.06
     limiting
    -0.06
    ario
    -0.06
    POSITIVE LOGITS
    розум
    0.08
    utenant
    0.07
     StObject
    0.07
     competent
    0.07
    ΕΤ
    0.07
     competency
    0.07
    .te
    0.07
     Meteor
    0.06
     onStop
    0.06
     mcc
    0.06
    Act Density 0.005%

    No Known Activations