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

    Neuronpedia

    INDEX
    Explanations

    Code and cost calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dataset
    -0.07
    .subtract
    -0.07
     MediaType
    -0.07
     fauc
    -0.06
     containers
    -0.06
    _handles
    -0.06
     stack
    -0.06
    .TRA
    -0.06
    _solution
    -0.06
     lineHeight
    -0.06
    POSITIVE LOGITS
    eldo
    0.06
    orage
    0.06
    рь
    0.06
     ingl
    0.06
    ylene
    0.06
    導
    0.06
    ár
    0.06
    uation
    0.06
    导
    0.06
     Rockies
    0.06
    Act Density 0.001%

    No Known Activations