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

    Neuronpedia

    INDEX
    Explanations

    airport codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irq
    -0.07
    :'
    -0.06
     Capitals
    -0.06
    UIT
    -0.06
     therapists
    -0.06
    ModelError
    -0.06
    nyder
    -0.06
    -ни
    -0.06
    sthrough
    -0.06
    "Yes
    -0.06
    POSITIVE LOGITS
     buildup
    0.07
    003
    0.07
     treasury
    0.06
     بايد
    0.06
     Meals
    0.06
     leads
    0.06
    获
    0.06
    snippet
    0.06
    _define
    0.06
     choice
    0.06
    Act Density 0.023%

    No Known Activations