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

    Neuronpedia

    INDEX
    Explanations

    species / animal facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ars
    0.27
    infty
    0.26
    sort
    0.26
     HL
    0.26
    celain
    0.26
     வண்ணப்பூச்சு
    0.26
    itate
    0.25
    registered
    0.25
     ହ
    0.25
     lcm
    0.25
    POSITIVE LOGITS
    Hosts
    0.32
    🧾
    0.29
    setType
    0.27
    类型
    0.27
     गोइंग
    0.26
    Niger
    0.26
    SBOM
    0.26
     nField
    0.26
    परि
    0.25
    Ис
    0.25
    Act Density 0.003%

    No Known Activations