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

    Neuronpedia

    INDEX
    Explanations

    eye protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LPARAM
    -0.07
     eleven
    -0.06
     cigars
    -0.06
    زار
    -0.06
     صور
    -0.06
     místo
    -0.06
     نت
    -0.06
     трьох
    -0.06
    ρή
    -0.06
    childs
    -0.06
    POSITIVE LOGITS
     observes
    0.06
     potions
    0.06
     XM
    0.06
    Om
    0.06
     emails
    0.06
    Ens
    0.06
     modification
    0.06
     Sno
    0.06
     Metodo
    0.06
    age
    0.06
    Act Density 0.004%

    No Known Activations