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

    Neuronpedia

    INDEX
    Explanations

    digital

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fty
    -0.07
    agle
    -0.07
     caves
    -0.06
    .Align
    -0.06
     --
    -0.06
     ISC
    -0.06
     Cooke
    -0.06
     IDM
    -0.06
     industries
    -0.06
     tits
    -0.06
    POSITIVE LOGITS
    ทางการ
    0.06
    .context
    0.06
    metal
    0.06
    증
    0.06
     distilled
    0.06
    implode
    0.06
     Femme
    0.06
    ालय
    0.06
     Laptop
    0.06
    �能
    0.06
    Act Density 0.008%

    No Known Activations