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

    Neuronpedia

    INDEX
    Explanations

    sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    инок
    -0.06
    >V
    -0.06
    Weight
    -0.06
    .Keys
    -0.06
    _SW
    -0.06
    BackgroundColor
    -0.06
     άλ
    -0.06
     UNIT
    -0.05
    _st
    -0.05
     dre
    -0.05
    POSITIVE LOGITS
     Chattanooga
    0.07
    todo
    0.07
     utilise
    0.07
     Giving
    0.07
    fe
    0.06
     logout
    0.06
     Thumb
    0.06
     є
    0.06
    091
    0.06
     affluent
    0.06
    Act Density 0.000%

    No Known Activations