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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EVT
    -0.07
    .latest
    -0.06
     dva
    -0.06
     september
    -0.06
     cyn
    -0.06
    tober
    -0.06
    .arch
    -0.06
    baseline
    -0.06
     Nob
    -0.06
    unched
    -0.06
    POSITIVE LOGITS
    'utilisateur
    0.07
    gable
    0.06
    undefined
    0.06
     grades
    0.06
     гля
    0.06
    helpers
    0.06
    'user
    0.06
     Alarm
    0.06
    ��
    0.06
    offset
    0.06
    Act Density 0.000%

    No Known Activations