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

    Neuronpedia

    INDEX
    Explanations

    Attributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hugged
    -0.07
    664
    -0.07
    hat
    -0.07
    шь
    -0.06
    919
    -0.06
    dates
    -0.06
     pixmap
    -0.06
    551
    -0.06
    412
    -0.06
    -lib
    -0.06
    POSITIVE LOGITS
    estruction
    0.06
    ly
    0.06
    }}"
    0.06
     instrumentation
    0.06
     دارند
    0.06
    }'.
    0.06
    ér
    0.06
    ,get
    0.06
     TRANSACTION
    0.06
    eliness
    0.06
    Act Density 0.035%

    No Known Activations