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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dr
    -0.06
     результате
    -0.06
    ्तव
    -0.06
     delegates
    -0.06
     наслід
    -0.06
    rians
    -0.06
     dz
    -0.06
    Reuters
    -0.06
    <GameObject
    -0.06
     repeats
    -0.06
    POSITIVE LOGITS
     wellbeing
    0.06
     Güney
    0.06
    385
    0.06
     undert
    0.06
    889
    0.06
     glance
    0.06
    953
    0.06
    �
    0.06
    เคย
    0.06
    fff
    0.06
    Act Density 0.015%

    No Known Activations