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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ratings
    -0.07
    .Reader
    -0.07
     monthly
    -0.07
     methodology
    -0.07
     methodologies
    -0.06
     chemistry
    -0.06
     Both
    -0.06
     Velocity
    -0.06
    checkpoint
    -0.06
     processor
    -0.06
    POSITIVE LOGITS
    ">&#
    0.07
    !!!!!!!!
    0.06
     маг
    0.06
    mailto
    0.06
    ีล
    0.06
     Caught
    0.06
    NJ
    0.06
     rou
    0.06
    Deleting
    0.06
    ,...
    0.06
    Act Density 0.014%

    No Known Activations