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

    Neuronpedia

    INDEX
    Explanations

    reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     условия
    -0.07
     carbs
    -0.07
     pancakes
    -0.06
     vest
    -0.06
     Arms
    -0.06
     CLEAN
    -0.06
     accumulate
    -0.06
     cocktail
    -0.06
     вихов
    -0.06
     nech
    -0.06
    POSITIVE LOGITS
     reporting
    0.15
     Reporting
    0.12
    Reporting
    0.09
     framing
    0.07
    .routing
    0.07
     messaging
    0.07
     datings
    0.06
    pection
    0.06
     DIM
    0.06
     labeling
    0.06
    Act Density 0.006%

    No Known Activations