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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    datepicker
    0.60
    的大小
    0.59
    await
    0.57
    Maggie
    0.55
    惜
    0.55
    rising
    0.55
    娩
    0.54
    ịp
    0.54
     Отече
    0.54
    Art
    0.53
    POSITIVE LOGITS
     material
    0.95
     behavior
    0.84
     attitude
    0.84
     stuff
    0.83
     behaviour
    0.82
     approach
    0.80
     restrictions
    0.78
     things
    0.77
     materiale
    0.76
     mindset
    0.75
    Act Density 0.000%

    No Known Activations