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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forum
    -0.06
    .bukkit
    -0.06
     Champagne
    -0.06
    Kn
    -0.06
     preschool
    -0.06
     Denis
    -0.06
     Dropbox
    -0.06
     genus
    -0.06
    fest
    -0.06
     Express
    -0.06
    POSITIVE LOGITS
     Liu
    0.07
    анием
    0.07
     chắn
    0.07
    previous
    0.06
     territory
    0.06
    -label
    0.06
     moż
    0.06
    <Animator
    0.06
    GBT
    0.06
    -animation
    0.06
    Act Density 0.163%

    No Known Activations