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

    Neuronpedia

    INDEX
    Explanations

    world locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MODIFIED
    -0.07
     batchSize
    -0.07
    Unchecked
    -0.07
    Lng
    -0.07
     Trials
    -0.07
     laid
    -0.07
    Don
    -0.06
     Loading
    -0.06
    دهای
    -0.06
     PIN
    -0.06
    POSITIVE LOGITS
    すれば
    0.07
    ={`/
    0.07
    soup
    0.06
    をした
    0.06
    ilos
    0.06
    todos
    0.06
     داشتند
    0.06
    _replace
    0.06
     fakat
    0.06
     dudes
    0.05
    Act Density 0.035%

    No Known Activations