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

    Neuronpedia

    INDEX
    Explanations

    latent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SMP
    -0.07
    @s
    -0.07
    Fri
    -0.06
    ustralian
    -0.06
     Pars
    -0.06
    GBT
    -0.06
    ophy
    -0.06
     pian
    -0.06
     آلات
    -0.06
    وث
    -0.06
    POSITIVE LOGITS
     gemeins
    0.06
    τών
    0.06
    缓
    0.06
     subsidized
    0.06
    โน
    0.06
     layoffs
    0.06
    UserID
    0.06
    iện
    0.06
    胜
    0.06
    325
    0.06
    Act Density 0.001%

    No Known Activations