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

    Neuronpedia

    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gro
    -0.07
     Hydro
    -0.07
    говор
    -0.06
    abbo
    -0.06
     обс
    -0.06
     axe
    -0.06
    ;;;;;;;;
    -0.06
     الثانية
    -0.06
    ораз
    -0.06
     kolo
    -0.06
    POSITIVE LOGITS
     japon
    0.07
    defense
    0.07
    Fortunately
    0.07
    kinson
    0.07
    --+
    0.07
     requ
    0.07
    -many
    0.07
    ước
    0.06
    814
    0.06
    contra
    0.06
    Act Density 0.000%

    No Known Activations